diff --git a/notebooks/Block_1/Solutions to Exercises Block 1 - Introduction to Image Classification.ipynb b/notebooks/Block_1/Solutions to Exercises Block 1 - Introduction to Image Classification.ipynb
index c7919ace21d9b1d60cd1056027355e565aa5e9cb..4a39fe9733ce753dbb06083da0c9d3dc2011daed 100644
--- a/notebooks/Block_1/Solutions to Exercises Block 1 - Introduction to Image Classification.ipynb	
+++ b/notebooks/Block_1/Solutions to Exercises Block 1 - Introduction to Image Classification.ipynb	
@@ -36,7 +36,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -47,28 +47,44 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Requirement already up-to-date: tensorflow_datasets in /opt/conda/lib/python3.7/site-packages (4.1.0)\n",
+      "Collecting tensorflow_datasets\n",
+      "  Downloading tensorflow_datasets-4.5.2-py3-none-any.whl (4.2 MB)\n",
+      "\u001b[K     |████████████████████████████████| 4.2 MB 5.1 MB/s eta 0:00:01\n",
+      "\u001b[?25hRequirement already satisfied, skipping upgrade: six in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (1.14.0)\n",
+      "Collecting dill\n",
+      "  Downloading dill-0.3.4-py2.py3-none-any.whl (86 kB)\n",
+      "\u001b[K     |████████████████████████████████| 86 kB 1.8 MB/s  eta 0:00:01\n",
+      "\u001b[?25hCollecting importlib-resources; python_version < \"3.9\"\n",
+      "  Downloading importlib_resources-5.4.0-py3-none-any.whl (28 kB)\n",
       "Requirement already satisfied, skipping upgrade: typing-extensions; python_version < \"3.8\" in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (3.7.4.3)\n",
-      "Requirement already satisfied, skipping upgrade: six in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (1.14.0)\n",
+      "Collecting promise\n",
+      "  Downloading promise-2.3.tar.gz (19 kB)\n",
+      "Collecting tensorflow-metadata\n",
+      "  Downloading tensorflow_metadata-1.6.0-py3-none-any.whl (48 kB)\n",
+      "\u001b[K     |████████████████████████████████| 48 kB 6.0 MB/s  eta 0:00:01\n",
+      "\u001b[?25hRequirement already satisfied, skipping upgrade: tqdm in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (4.45.0)\n",
+      "Requirement already satisfied, skipping upgrade: requests>=2.19.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (2.23.0)\n",
       "Requirement already satisfied, skipping upgrade: termcolor in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (1.1.0)\n",
-      "Requirement already satisfied, skipping upgrade: future in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (0.18.2)\n",
-      "Requirement already satisfied, skipping upgrade: tqdm in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (4.45.0)\n",
-      "Requirement already satisfied, skipping upgrade: importlib-resources; python_version < \"3.9\" in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (3.3.0)\n",
-      "Requirement already satisfied, skipping upgrade: absl-py in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (0.11.0)\n",
-      "Requirement already satisfied, skipping upgrade: attrs>=18.1.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (19.3.0)\n",
-      "Requirement already satisfied, skipping upgrade: protobuf>=3.6.1 in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (3.13.0)\n",
+      "Requirement already satisfied, skipping upgrade: protobuf>=3.12.2 in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (3.19.4)\n",
       "Requirement already satisfied, skipping upgrade: numpy in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (1.19.1)\n",
-      "Requirement already satisfied, skipping upgrade: requests>=2.19.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (2.23.0)\n",
-      "Requirement already satisfied, skipping upgrade: tensorflow-metadata in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (0.25.0)\n",
-      "Requirement already satisfied, skipping upgrade: promise in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (2.3)\n",
-      "Requirement already satisfied, skipping upgrade: dill in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (0.3.3)\n",
-      "Requirement already satisfied, skipping upgrade: zipp>=0.4; python_version < \"3.8\" in /opt/conda/lib/python3.7/site-packages (from importlib-resources; python_version < \"3.9\"->tensorflow_datasets) (3.1.0)\n",
-      "Requirement already satisfied, skipping upgrade: setuptools in /opt/conda/lib/python3.7/site-packages (from protobuf>=3.6.1->tensorflow_datasets) (46.1.3.post20200325)\n",
+      "Requirement already satisfied, skipping upgrade: absl-py in /opt/conda/lib/python3.7/site-packages (from tensorflow_datasets) (1.0.0)\n",
+      "Requirement already satisfied, skipping upgrade: zipp>=3.1.0; python_version < \"3.10\" in /opt/conda/lib/python3.7/site-packages (from importlib-resources; python_version < \"3.9\"->tensorflow_datasets) (3.1.0)\n",
+      "Collecting googleapis-common-protos<2,>=1.52.0\n",
+      "  Downloading googleapis_common_protos-1.55.0-py2.py3-none-any.whl (212 kB)\n",
+      "\u001b[K     |████████████████████████████████| 212 kB 40.3 MB/s eta 0:00:01\n",
+      "\u001b[?25hRequirement already satisfied, skipping upgrade: idna<3,>=2.5 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tensorflow_datasets) (2.9)\n",
+      "Requirement already satisfied, skipping upgrade: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tensorflow_datasets) (1.25.9)\n",
       "Requirement already satisfied, skipping upgrade: chardet<4,>=3.0.2 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tensorflow_datasets) (3.0.4)\n",
-      "Requirement already satisfied, skipping upgrade: idna<3,>=2.5 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tensorflow_datasets) (2.9)\n",
       "Requirement already satisfied, skipping upgrade: certifi>=2017.4.17 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tensorflow_datasets) (2020.6.20)\n",
-      "Requirement already satisfied, skipping upgrade: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tensorflow_datasets) (1.25.9)\n",
-      "Requirement already satisfied, skipping upgrade: googleapis-common-protos<2,>=1.52.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow-metadata->tensorflow_datasets) (1.52.0)\n"
+      "Building wheels for collected packages: promise\n",
+      "  Building wheel for promise (setup.py) ... \u001b[?25ldone\n",
+      "\u001b[?25h  Created wheel for promise: filename=promise-2.3-py3-none-any.whl size=21495 sha256=9675d5917247a843670272d14b85c27811d276d4f06faeb1bc0a545e304f40d5\n",
+      "  Stored in directory: /home/jovyan/.cache/pip/wheels/29/93/c6/762e359f8cb6a5b69c72235d798804cae523bbe41c2aa8333d\n",
+      "Successfully built promise\n",
+      "Installing collected packages: dill, importlib-resources, promise, googleapis-common-protos, tensorflow-metadata, tensorflow-datasets\n",
+      "Successfully installed dill-0.3.4 googleapis-common-protos-1.55.0 importlib-resources-5.4.0 promise-2.3 tensorflow-datasets-4.5.2 tensorflow-metadata-1.6.0\n",
+      "\u001b[33mWARNING: You are using pip version 20.2.4; however, version 22.0.3 is available.\n",
+      "You should consider upgrading via the '/opt/conda/bin/python3 -m pip install --upgrade pip' command.\u001b[0m\n"
      ]
     }
    ],
@@ -78,7 +94,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -89,7 +105,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2.1.0\n"
+      "2.7.1\n"
      ]
     }
    ],
@@ -123,7 +139,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -143,7 +159,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -184,31 +200,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1mDownloading and preparing dataset mnist/3.0.1 (download: 11.06 MiB, generated: 21.00 MiB, total: 32.06 MiB) to /home/jovyan/tensorflow_datasets/mnist/3.0.1...\u001b[0m\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:absl:Dataset mnist is hosted on GCS. It will automatically be downloaded to your\n",
-      "local data directory. If you'd instead prefer to read directly from our public\n",
-      "GCS bucket (recommended if you're running on GCP), you can instead pass\n",
-      "`try_gcs=True` to `tfds.load` or set `data_dir=gs://tfds-data/datasets`.\n",
-      "\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "\u001b[1mDownloading and preparing dataset 11.06 MiB (download: 11.06 MiB, generated: 21.00 MiB, total: 32.06 MiB) to /home/jovyan/tensorflow_datasets/mnist/3.0.1...\u001b[0m\n",
       "\u001b[1mDataset mnist downloaded and prepared to /home/jovyan/tensorflow_datasets/mnist/3.0.1. Subsequent calls will reuse this data.\u001b[0m\n"
      ]
     }
@@ -235,7 +234,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -254,7 +253,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -282,7 +281,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -321,7 +320,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -386,7 +385,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -397,9 +396,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "\u001b[1mDownloading and preparing dataset fashion_mnist/3.0.1 (download: 29.45 MiB, generated: 36.42 MiB, total: 65.87 MiB) to /home/jovyan/tensorflow_datasets/fashion_mnist/3.0.1...\u001b[0m\n",
-      "Shuffling and writing examples to /home/jovyan/tensorflow_datasets/fashion_mnist/3.0.1.incompleteBQL5KX/fashion_mnist-train.tfrecord\n",
-      "Shuffling and writing examples to /home/jovyan/tensorflow_datasets/fashion_mnist/3.0.1.incompleteBQL5KX/fashion_mnist-test.tfrecord\n",
+      "\u001b[1mDownloading and preparing dataset 29.45 MiB (download: 29.45 MiB, generated: 36.42 MiB, total: 65.87 MiB) to /home/jovyan/tensorflow_datasets/fashion_mnist/3.0.1...\u001b[0m\n",
       "\u001b[1mDataset fashion_mnist downloaded and prepared to /home/jovyan/tensorflow_datasets/fashion_mnist/3.0.1. Subsequent calls will reuse this data.\u001b[0m\n"
      ]
     }
@@ -475,7 +472,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 11,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -501,7 +498,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 12,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -536,7 +533,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 13,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -582,7 +579,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 14,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -625,7 +622,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -653,7 +650,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
@@ -716,7 +713,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -884,7 +881,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -894,7 +891,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -903,7 +900,7 @@
        "(500, 5000)"
       ]
      },
-     "execution_count": 20,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -915,7 +912,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -924,7 +921,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
@@ -945,19 +942,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
-     "ename": "ModuleNotFoundError",
-     "evalue": "No module named 'seaborn'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-23-77ec2383cc69>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m# utility function for plotting confusion matrix\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmatplotlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpyplot\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mseaborn\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0msns\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      4\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmetrics\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mconfusion_matrix\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'seaborn'"
-     ]
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 648x648 with 2 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
     }
    ],
    "source": [
@@ -994,7 +992,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1004,9 +1002,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 24,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(500, 5000)"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "dists = classifier.compute_distances_no_loops(X_test)\n",
     "dists.shape"
@@ -1014,7 +1023,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1023,9 +1032,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 26,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Got 400 / 500 correct => accuracy: 0.800000\n"
+     ]
+    }
+   ],
    "source": [
     "num_test = X_test.shape[0]\n",
     "\n",
@@ -1036,9 +1053,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 27,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 648x648 with 2 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "plot_confmat(y_test, y_test_pred) "
    ]
@@ -1052,7 +1082,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1066,7 +1096,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1076,7 +1106,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1086,7 +1116,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1095,7 +1125,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1115,9 +1145,51 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 33,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "k = 1, accuracy = 0.809000\n",
+      "k = 1, accuracy = 0.809000\n",
+      "k = 1, accuracy = 0.812000\n",
+      "k = 1, accuracy = 0.780000\n",
+      "k = 1, accuracy = 0.790000\n",
+      "k = 4, accuracy = 0.811000\n",
+      "k = 4, accuracy = 0.834000\n",
+      "k = 4, accuracy = 0.842000\n",
+      "k = 4, accuracy = 0.806000\n",
+      "k = 4, accuracy = 0.799000\n",
+      "k = 5, accuracy = 0.804000\n",
+      "k = 5, accuracy = 0.828000\n",
+      "k = 5, accuracy = 0.839000\n",
+      "k = 5, accuracy = 0.807000\n",
+      "k = 5, accuracy = 0.805000\n",
+      "k = 10, accuracy = 0.810000\n",
+      "k = 10, accuracy = 0.827000\n",
+      "k = 10, accuracy = 0.832000\n",
+      "k = 10, accuracy = 0.805000\n",
+      "k = 10, accuracy = 0.803000\n",
+      "k = 12, accuracy = 0.808000\n",
+      "k = 12, accuracy = 0.818000\n",
+      "k = 12, accuracy = 0.833000\n",
+      "k = 12, accuracy = 0.802000\n",
+      "k = 12, accuracy = 0.802000\n",
+      "k = 18, accuracy = 0.804000\n",
+      "k = 18, accuracy = 0.810000\n",
+      "k = 18, accuracy = 0.832000\n",
+      "k = 18, accuracy = 0.798000\n",
+      "k = 18, accuracy = 0.791000\n",
+      "k = 20, accuracy = 0.799000\n",
+      "k = 20, accuracy = 0.806000\n",
+      "k = 20, accuracy = 0.822000\n",
+      "k = 20, accuracy = 0.797000\n",
+      "k = 20, accuracy = 0.787000\n"
+     ]
+    }
+   ],
    "source": [
     "for k in sorted(k_to_accuracies):\n",
     "    for accuracy in k_to_accuracies[k]:\n",
@@ -1126,9 +1198,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 34,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEWCAYAAAB8LwAVAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/d3fzzAAAACXBIWXMAAAsTAAALEwEAmpwYAAA8L0lEQVR4nO3deXxV1bXA8d/KHAJJgARImGdBREEUUVHRCihF0LYW+izqU7GtKGprq6+WR31trdo6VduKtlWpglSRoWDRtohUERnCIPMgCCRAUMMQyLzeH+fccBNukpPkDhnW9/O5n3vPPtO6l8tdOXvvs7eoKsYYY0xlUZEOwBhjTMNkCcIYY0xAliCMMcYEZAnCGGNMQJYgjDHGBGQJwhhjTECWIIypIxHpJiIqIjHu8jsicrOXbetwrv8RkZfqE2+oicjLIvKLSMdhgscShAk7EfmOiKwWkRMikuP+sF4a6bjqS1WvUdVX6nscEblCRPZXOvavVPX2+h7bmNqwBGHCSkTuB54GfgW0B7oAvwfGVbF9nf7iNsbUnyUIEzYikgI8AtylqnNVNV9Vi1V1oao+4G4zXUTeFJG/isgx4BYRyRSRBSLypYjsFJE7/I55oXs1ckxEDonIk255gnuML0QkT0RWiUj7ADF9W0RWVyq7T0QWuK/HiEiWe/x9IjK9mvf3vojc7r6OFpHfiMgREdkNjKm07a0iskVEjovIbhG50y1PAt4BMt0rrBPu+58uIn/12/86Ednkvrf3RaSf37o9IvIjEdkgIkdF5A0RSagi5igReVhE9orIYRF51f138q8Wu1lEPnffy0+rev+VjttKRJaKyLMiIl72MQ2PJQgTTsOABODtGrYbB7wJpAKvAbOB/UAm8E3gVyJypbvtM8AzqpoM9ATmuOU3AylAZ6At8D3gVIBzLQT6ikhvv7LvAK+7r/OBSW4sY4Dvi8j4Gt8p3AF8HRgEDHHj9nfYXZ8M3Ao8JSKDVTUfuAbIVtWW7iPbf0cR6QPMAu4F0oHFwEIRifPb7EZgNNAdGAjcUkWct7iPEUAPoCXwXKVtLgX6AlcB0/yTUSAi0hb4F/Chqt6jNp5Po2UJwoRTW+CIqpbUsN0KVZ2nqmVAGnAJ8BNVLVDVdcBLOD/aAMVALxFJU9UTqvqxX3lboJeqlqrqGlU9VvlEqnoSmA9MBHATxVnAAnf9+6q6UVXLVHUDzg/z5R7e643A06q6T1W/BB6tdN5FqrpLHcuAd4HhHo4L8G1gkaq+p6rFwG+AROBiv22eVdVs99wLgfOqONZ/AU+q6m5VPQE8BEyoVLX3c1U9parrgfXAudXElgksA/6mqg97fD+mgbIEYcLpCyDNQ7vCPr/XmcCXqnrcr2wv0NF9fRvQB9jqViN93S2fCSwBZotItog8LiKxIjLcr+pmk7vt67gJAufqYZ6bOBCRoW5VSa6IHMW5Eknz8F4zK72Pvf4rReQaEfnYrTbLA671eFzfscuP5ybSfZz+TAAO+r0+iXNlUOOx3NcxOO1DtT0WOFdZicAfq9nGNBKWIEw4rQAKgfE1bOdfJZENtBGRVn5lXYADAKq6Q1UnAu2Ax4A3RSTJbdv4uar2x/nL+uvAJFVd7ld1c7Z7vPeAdBE5DydRvO53rtdxriY6q2oKzg+flzr1HJzqLf+YARCReOAtnL/826tqKk41ke+4NVXJZANd/Y4n7rkOeIir2mO5cZYAh+pwLIAXgX8Ai932FNOIWYIwYaOqR4FpwPMiMl5EWrh/1V8jIo9Xsc8+4CPgUbfheSDOVcNfAUTkJhFJd/+KznN3KxORESJyjohEA8dwqpzKqjhHMfA34AmgDU7C8GmFcwVTICIX4lxheDEHuEdEOolIa+BBv3VxQDyQC5SIyDXASL/1h4C2vsbiKo49RkSuEpFY4Ic4ifcjj7H5mwXcJyLdRaQlTu+yNzxUA1ZnCrANp10ksR7HMRFmCcKElar+FrgfeBjnB3Ifzg/KvGp2mwh0w/lr923gf1X1n+660cAmETmB02A9QVVPAR1wGrqPAVtw6sVnVnOO14Gv4dSd+/84/gB4RESO4yS3OYF2DuBFnCqu9cBaYK5vhVtddo97rK9wks4Cv/VbcX64d7u9lDL9D6yq24CbgN8BR4CxwFhVLfIYm78/43wuHwCfAQXA3XU4jn98CkzG6Vgwv6oeVKbhE+tgYIwxJhC7gjDGGBOQJQhjjDEBWYIwxhgTkCUIY4wxATWZgdDS0tK0W7dukQ7DGGMalTVr1hxR1fRA65pMgujWrRurV6+ueUNjjDHlRGRvVeusiskYY0xAliCMMcYEZAnCGGNMQJYgjDHGBGQJwhhjTECWIBq7DXPgqQEwPdV53uB1LDljjKlek+nm2ixtmAML74FidybNo/ucZYCBN0YuLmNMk2BXEI3Zvx45nRx8ik855cYYU0+WIBqzo/trV26MMbVgCaIxS+lUu3JjjKkFSxCN2VXTILbSjI6xiU65McbUU0gThIiMFpFtIrJTRB4MsL6LiCwVkSwR2SAi1wZYf0JEfhTKOButgTfC2GchpTMgzvPYZ62B2hgTFCHrxeROFv88cDXO3LSrRGSBqm722+xhYI6q/kFE+gOLceYe9nkSeCdUMTYJA2+0hGCMCYlQXkFcCOxU1d3uZOqzgXGVtlEg2X2dgjMpPQAiMh5nEvVNIYzRGGNMFUKZIDoC+/yW97tl/qYDN4nIfpyrh7sBRKQl8BPg5yGMzxhjTDUi3Ug9EXhZVTsB1wIzRSQKJ3E8paonqttZRCaLyGoRWZ2bmxv6aJugRbsXMfLNkQx8ZSAj3xzJot2LIh2SMaaBCOWd1AeAzn7Lndwyf7cBowFUdYWIJABpwFDgmyLyOJAKlIlIgao+57+zqs4AZgAMGTJEQ/EmmrJFuxcx/aPpFJQWAJCTn8P0j6YDMKbHmAhGZoxpCEJ5BbEK6C0i3UUkDpgALKi0zefAVQAi0g9IAHJVdbiqdlPVbsDTwK8qJwdTf8+sfaY8OfgUlBbwzNpnIhSRMaYhCVmCUNUSYAqwBNiC01tpk4g8IiLXuZv9ELhDRNYDs4BbVNWuBMLkYP7BWpUbY5qXkA7Wp6qLcRqf/cum+b3eDFxSwzGmhyQ4Q4ekDuTk5wQsN8aYSDdSmwiaOngqCdEJFcoSohOYOnhqhCIyxjQkNtx3M+ZriH5m7TMczD9Ih6QOTB081RqojTGAJYhmb0yPMZYQjDEBWRWTMcaYgCxBGGOMCcgShDHGmIAsQRhjjAnIEoQxxpiALEEYY4wJyBKEMcaYgCxBNAHffmEF335hRaTDMMY0MZYgGrsNc2D/KtjzH3hqgLNsjDFBYAmiMdswBxbeAyWFzvLRfc6yJQljTBBYgmjM/vUIFJ+qWFZ8yik3xph6srGYGrOj+2tXbpqc7SsPsmL+Lk58WUjLNvEMG9eTPkNtuHYTHHYF0ZildKpduWlStq88yNLXtnLiS6eK8cSXhSx9bSvbV9qETyY4LEE0ZldNg9jEimWxiU65afJWzN9FSVFZhbKSojJWzN8VoYhMU2NVTI3ZwBud578ddBqqUzo7ycFXbkLu6MKFHH7qaUpycojJyKDdffeSMnZsWM7tu3LwWm6Cb8vypSyf/SrHvzhCq7ZpDJ8wiX7DR0Q6rKCxBNHYDbwRVrj3QNz5QGRjaWaOLlxIzs+moQUFAJRkZ5PzM+fqLRxJomWb+IDJoGWb+JCf2zjJ4d0Zz1FS5PwbHD+Sy7szngNoMknCqpiMqaPDTz1dnhx8tKCAw089HZbzDxvXk5i4iv+FY+KiGDauZ1jO39wtn/1qeXLwKSkqZPnsVyMUUfDZFYQxdVSSk1Or8mDz9VayXkyRcfyLI7Uqb4wsQRhTRzEZGZRkZwcsD5c+QztYQoiQVm3TOH4kN2B5U2FVTMbUUbv77kUSEiqUSUIC7e67NzIBmbAaPmESMXEV23ti4uIZPmFShCIKvpAmCBEZLSLbRGSniDwYYH0XEVkqIlkiskFErnXLLxSRde5jvYhcH8o4jamLlLFjyfi/R4jJzAQRYjIzyfi/R8LWi8lEVr/hIxg5eQqt0tJBhFZp6YycPKXJNFBDCKuYRCQaeB64GtgPrBKRBaq62W+zh4E5qvoHEekPLAa6AZ8CQ1S1REQygPUislBVS0IVb3PmGwn2jTuHRTiSxidl7FhLCM1Yv+EjmlRCqKzGKwgRWSMid4lI61oe+0Jgp6ruVtUiYDYwrtI2CiS7r1OAbABVPemXDBLc7YwxxoSRlyqmbwOZOFcAs0VklIiIh/06Avv8lve7Zf6mAzeJyH6cq4e7fStEZKiIbAI2At+zqwdjjAmvGhOEqu5U1Z8CfYDXgT8De0Xk5yLSpp7nnwi8rKqdgGuBmSIS5Z53paqeDVwAPCQiCZV3FpHJIrJaRFbn5p7Zm8AYY0zdeWqkFpGBwG+BJ4C3gG8Bx4B/V7PbAaCz33Int8zfbcAcAFVdgVOdVKGPmKpuAU4AAyqfQFVnqOoQVR2Snp7u5a0YY4zxqMZGahFZA+QBfwIeVFXfrYMrReSSanZdBfQWke44iWEC8J1K23wOXAW8LCL9cBJErrvPPreRuitwFrDH87syxhhTb16uIL6lqlep6ut+yQEAVb2hqp3cNoMpwBJgC05vpU0i8oiIXOdu9kPgDhFZD8wCblFVBS7F6bm0Dngb+IGqNp3bExuQRbsXsSF3A6sPrWbkmyNZtHtRpEMyxjQQXrq53i4ij6tqHoDbm+mHqvpwTTuq6mKcxmf/sml+rzcDZ1yFqOpMYKaH2Ew9LNq9iOkfTaeozLmxJyc/h+kfTQdgTI8xEYzMGNMQeLmCuMaXHABU9SucBmXTyD2z9hkKSisONldQWsAza5+JUETGmIbES4KIFpHy+8lFJBGw8YSbgIP5gWceq6rcnOnowoXsuPIqtvTrz44rr+LowoWRDsmYoPFSxfQa8C8R+Yu7fCvwSuhCMuHSIakDOflnjjzaIckGf/Mi0vNBGBNqXu6DeAz4JdDPffyfqj4e6sBM6E0dPJWE6Iq3lyREJzB18NQIRdS4+OaD+PGl3+fHl34fCO98EMaEmqexmFT1HeCdEMdiwszXEP2jPfspKisiIymDqYOnWgO1R5GeD8KYUPNyH8RFwO9wrh7igGggX1WTq93RNApjeozh1XR3sL5v3l3D1sZfQ5gPwphQ8tJI/RzOkBg7gETgdpxRWo1p1mw+CNPUea1i2iki0apaCvxFRLKAh0IbmjENm68hWt45gBYVEZOZSbv77rUGatNkeEkQJ0UkDlgnIo8DOdhMdMYATpJIzHaq6Hq/dE+EozEmuLz80H/X3W4KkI8zAN83QhmUMcaYyKv2CsKdFe5XqvpfQAHw87BEZYwxJuKqvYJw2xy6ulVMxhhjmhEvbRC7gQ9FZAFOFRMAqvpkyKIyxnhmc4qbUPGSIHa5jyigVWjDMcYY01DUmCBU1dodjDGmGfJyJ/VSQCuXq+qVIYnIGGNMg+CliulHfq8TcLq4loQmHGOMMQ2FlyqmNZWKPhSRT0IUjzHGGI/ysw5zbMkeSvMKiU6NJ3lUN5IGtQva8b1UMbXxW4wCzgdSghaBMcaYWsvPOkze3B1ocRkApXmF5M3dARC0JOGlimkNThuE4FQtfQbcFpSzG2OMqZNjS/aUJwcfLS7j2JI94UsQqto9KGcyxhgTNKV5hbUqr4sax2ISkbtEJNVvubWI/CBoERhjjKm16NT4WpXXhZfB+u5Q1Tzfgqp+BdwRtAiMMcbUWvKobkhsxZ9wiY0ieVS3oJ3DS4KIFhEpD8AZwM/T2EwiMlpEtonIThF5MMD6LiKyVESyRGSDiFzrll8tImtEZKP7bPdcGGMapG+/sKJ8uJNwShrUjtQbepdfMUSnxpN6Q+/w9mIC/gG8ISIvuMt3umXVchPJ88DVwH5glYgsUNXNfps9DMxR1T+ISH9gMdANOAKMVdVsERkALAE6enxPxhjTLCQNahfUhFCZlwTxE2Ay8H13+T3gJQ/7XQjsVNXdACIyGxgH+CcIBXxzW6cA2QCqmuW3zSYgUUTiVTV4rS/GGGOq5SVBJAIvquofofzKIB44WcN+HYF9fsv7gaGVtpkOvCsidwNJwNcCHOcbwNpAyUFEJuMkL7p06VLjGzHGGOOdlzaIf+EkCZ9E4J9BOv9E4GVV7QRcC8wUkfKYRORs4DGcaq0zqOoMVR2iqkPS09ODFJIxxhjwliASVPWEb8F93cLDfgdwpif16eSW+bsNmOMedwXOWE9pACLSCXgbmKSquzyczxhjTBB5SRD5IjLYtyAi5wOnPOy3CugtIt3dGekmAAsqbfM5cJV73H44CSLXve9iEfCgqn7o4VzGGGOCzEuCuBf4m4gsF5H/AG8AU2raSVVL3O2WAFtweittEpFHROQ6d7MfAneIyHpgFnCLqqq7Xy9gmoiscx+ha6pv5E4VlVJSWlbzhqbJ2b7yIIc+O0r2jjxe+Z8P2b7yYKRDMk2Il6E2VonIWUBft2ibqhZ7ObiqLsbpuupfNs3v9WbgkgD7/QL4hZdzNHcfbM9lw4GjCPC9mWsYP6gjI85KJz4mOtKhmRDbvvIgS1/bSmmcM13LiS8LWfraVgD6DO0QydBME+GlFxM4yaE/ThXQYBFBVV8NXVjGi8+O5DPl9bUkxkaTkhjD6r1f8Y9NB0lOiGHMwAzGn9eRC7q1ISpKaj6YaXRWzN9FSVFZhdtWS4rKWDF/lyUIExRehvv+X+AKnASxGLgG+A9gCSKCjhUUc/srq4iJjqJHWiLxsdG8dvtQPtz1BfOyDjB/XTazPtlHx9RErjsvk+sHdaRPe5tSvCk58WXg24KqKjemtrxcQXwTOBfIUtVbRaQ98NfQhmWqU1qmTJ2Vxd4vTvLX24fy1HvbAYiJjuLyPulc3iedk0UlvLf5EG9nHWDGB7v5w/u76J+RzPhBmVx3bkc6pCRE+F2Y+mrZJj5gMmjZJniDtZnmzUuCOKWqZSJSIiLJwGEqdl81Yfb4kq0s3ZbLL8YP4KIebQNu0yIuhnHndWTceR05cqKQv6/P5u112fxq8VYefWcrF/dsy7jzOnLNAKuKaKyGjetZ3ubgExMXxbBxPSMUkWlqvCSI1W630xdxJg86AYR/ZCoDwNtZ+3lh2W5uuqgLN13U1dM+aS3jueWS7txySXd2555g3rps5q87wI/f3MDP5n1KUnwMibHRvLR8Ny3iYkiKjyYpLoYW7nNSfDRJ8THOurhoYqK9dH4zoeZrZ5j19jpKS5SWbeIZNq6ntT+YoPHSi8k398MfReQfQLKqbghtWCaQ9fvy+MlbG7moRxv+d+zZdTpGj/SW3H91H+77Wm+y9uUxL+sAr6/8nC/zi/jFoi2ejhEXE0XL+BhaxJ1OJJWXncTilrnPLX1JJj76dCKKj6FFrCWduuoztAPt1zkzAN9857AIR2OaGq+9mABQ1T0hisPU4NCxAibPXE27VvH8/r/OJ7aeP6giwuAurRncpTXbDh5HVXnx5gs4WVRCfmFp+XN+YQn5RSWcLHJf+9YVlXCysJR8d7sThSUcPlboLpeQX1RKUYn3ezPiY6JIive7evFLLEnxMWcknqS4aFq4z5XX+56jrfeWMfVSqwRhIqOguJTJM9dwvKCEuT+4mDZJnqbjqBURISUxlpTE2KAds7i0jJNFvmTjJpxKicU/IZ0oPJ2IThaVcryghEPHCvySUu2STkJsVOArmgpXPaeTTUu/K5sWcTGnr4rc5xaWdEwzYwmigVNV/mfuRtbvy+OPN53PWR2Sa96pgYiNjiIlMSqoSaeopIxTRW6iKSrhRGEpJ90rlqqvek6v9086vmRVVIu70BNjo8sTiK/abMfhEyTGRrN8Ry4XdGtDQqzdpGiaBk8Jwh3iu73/9qr6eaiCMqe9tPwz5mYd4P6r+zDaehwRFxNFXEwUKS2Cm3R8VyjlyabQ74rGTSTOcsXt8gtLKCkt49CpYr77p09IiI3ioh5tuax3Opf3TadHWhJ+EzIa06h4uVHubuB/gUOA708tBQaGMC4DvL/tMI++s4Vrz+nA3Vf2inQ4TZaTdOJI9TJGcQDffmEFpWXKD0b05IPtR1i2PZdHtm2Gv0PH1EQuc+9NubhXW5ITgpfYjAk1L1cQU4G+qvpFqIMxp+3KPcHds7Lo2yGZ33zrXPsrtIGLjhKuPKs9V57VHoB9X55k2fZclm3PZeH6bGZ98jnRUcLgLqlc3iedy/qkMyAzxYZBMQ2alwSxDzga6kDMaUdPFXPHK6uJi47ixUnn0yLOmooam85tWnDTRV256aKuFJeWsXbvVyzbnssHO3L5zbvb+c2722mTFMfw3mlc1jud4X3SaNfK7m43DYuXX57dwPsisggov69fVZ8MWVTNWGmZcvesLPZ9dZLX77iITq3rWO9hGozY6CiG9mjL0B5t+fHos8g9Xsh/dubywfYjLN+Ry/x12QD0z0jmsj7pXNYnjSFd2xAXY/eGmMjykiA+dx9xVBg30oTCr9/Zwgfbc3n0hnO4oFubSIdjQiC9VTzXD+rE9YM6UVambM455lxdbM/lpeW7+eOyXSTFRTOsZ9vy9ouubZMiHbZpoL79gjOwxRshuFHSy53UPwcQkZbu8onq9zB19daa/by4/DNuHtaViRd2iXQ4JgyiooQBHVMY0DGFu0b04nhBMSt2fcEHO5z2i39uOQxA17YtnJ5RfdIZ1rMtSfFW7WhCz0svpgHATKCNu3wEZ57oTSGOrVlZ+/lXPDR3Ixf3bMvDX+8f6XBMhLRKiGXk2R0YeXYHVJU9X5zkA7ex+801+5n58V5io4Xzu7bm8j7tuKxPGqpqnRhMSHj5M2QGcL+qLgUQkStwBu67OHRhhc+8rAM8sWQb2XmnyExN5IFRfRk/qGNYYzh4tIA7Z66hQ0oCz39ncL2H0TBNg4jQPS2J7mlJ3HxxNwpLSlmz56vy3lGP/WMrj/0DYqOFlvExPPuvHfTPSKZfZjKZKQmWNEy9eUkQSb7kAKCq74tIk6gQnZd1gIfmbuRUcSkAB/JO8dDcjQBhSxIFxaXcOXM1JwtL+OttQ2kdgmE0TNMQHxPNxb3SuLhXGg9d249Dxwr4YHsuv35nKycKS3jSnRcEICUx1kkWGcn0z0ymX0YrerdrZQ3fplY89WISkZ/hVDMB3ITTs6nRe2LJtvLk4HOquJQnlmwLS4JQVR58awMbDhxlxneH0LeDzfhmvGufnMC3hnTmzTX7AfjTLRew7eAxNmcfY3POMTbnHOf1T/ZSUOzc3xobLfRMb0n/zGT6ZySXJxD7o8RUxUuC+G/g58Bcd3m5W9boZeedqlV5sL3wwW7mrcvmRyP7cHX/9nU7yIY5sP8glBTCU3fAVdNg4I3BDdQ0Ci3jYzi/axvO73q691tpmfLZkXw25xxjS46TPP6z4whz1x4o3yYjJaHS1UYyXdu0sJv4jKdeTF8B94QhlrDLTE3kQIBkkJmaGPJzL916mMf+sZWvD8zgrhF1HEZjwxxYeA+U/NBZPrrPWQZLEgZw7vDu1a4lvdq15LpzM8vLc48XssWXNNzn97fnUlqmACTFRXNWhlM11T8jhX4ZrTirQzKJcTYQYXNSZYIQkadV9V4RWYgz9lIFqnpdSCMLgwdG9a3QBgHOaJ0PjOob0vPuPHyce2Zl0T8jmSe+WY9hNP71CBRXSnDFp5xySxCmGumt4klv5Qz54VNQXMqOQyfYnHOULTnH2Zx9jPlZ2fz1Y2dcziiBbmlJFa42zs5IJr1VvDWIN1HVXUH42hx+U9eDi8ho4BkgGnhJVX9daX0X4BUg1d3mQVVdLCJtgTeBC4CXVXVKXWOojq+d4cdvbqCotIyOYejFdPRkMbe/spr42ChenDSkfn+RHd1fu3ITdEcXLuTU+gNoURE73niYdvfdS8rYsZEOq04SYqM5p1MK53RKKS9TVfZ/dYpN2aevNtbty+PvG3LKt2mbFFdeNeVLHj3Sk5pFb7wty5eSs2MvpSXFzLhrBsMnTKLf8BGRDitoqkwQqrrGfXmeqj7jv05EpgLLqjuwO0T488DVwH5glYgsUNXNfps9DMxR1T+ISH9gMdANKAB+BgxwHyEzflBHZn3i/IUUijsR/ZWUljFl1loO5J1i1h0X1b8qK6WTU60UqNyE3NGFC8n52TR0yK0AlGRnk/OzaQCNNklUJiJ0btOCzm1aVBhu/uipYrb6VU9tzjnGyx/uKZ9bIy4mij7tW56+2nC73zal0Wy3LF/KuzOeo7TNKACOH8nl3RnPATSZJOGlkfpmnKsAf7cEKKvsQmCnqu4GEJHZwDjAP0Eo4JsBJwXIBlDVfOA/ItKkxrh+9J2tLN9xhMe/MZAhwRhG46ppTptDoV9ZbKJTbkLu8FNPowUFFcq0oIDDTz3dZBJEVVISY8vHl/IpLi1jd25+hSqqf245zJzVp69oO7VOrFBF1T8jmU6tExtlFdXy2a9SUlRYoaykqJDls19t+glCRCYC3wG6i8gCv1WtgC89HLsjzkiwPvuBoZW2mQ686845kQR8zcNx/WOcDEwG6NKlbkNTPDxvIys/c95Oz4cWM3FoZ34x/pw6Has6c1bv40//+YxbL+nGjRd0Ds5Bfe0Mf3N7MaV0tl5MYVSSk1Or8qYuNjqKvh1a0bdDK64f5JSpKoePFzrdbv2qqd7bcgh1WzZbJcTQr8PphNEvI5ne7Vs2+Jn5jn9xpFbljVF1VxAfATlAGvBbv/LjwIYgnX8iThvDb0VkGDBTRAaoqqc5IFV1Bs6d3gwZMuSMhvSaPDxvY3kDHECpavlyMJPEmr1f8fDbn3JprzR+em2/oB0XcJLBCmewLu58ILjHNtWKycigJDs7YLlxiAjtkxNon5zAiL7tystPFpWw7eDxCt1v56zex8kip8NIdJTQMz3pjO63aS3jI/VWztCqbRrHj+QGLG8qqmuD2AvsBepaMX8A8P9TuZNb5u82YLR7vhUikoCTkA7X8Zy1MmtlgPp7tzxYCSLn6CnunLmGjNQEnvvOIGKaQcNdc9HuvnvL2xx8JCGBdvfdG5mAGpEWcTEM6tKaQV1al5eVlSl7vzxZnjC25Bxj5WdfMm/d6STcrlX8GQ3i3dOSiI7APRvDJ0wqb3PwiYmLZ/iESWGPJVS8DNZ3EfA7oB/OcN/RQL6qJle7I6wCeotId5zEMAGnysrf58BVwMsi0g9IAM5MySFSqoEvOqoqr61TRaVMfnUNBcWlzLpjKKkt7I7VpsTXziDvOL2YYjIzG3UvpkiLijo99tS155y+Cvsqv6i8amqz381+Je49GwmxUfTt4N4dnplMf/eejVCPeOtrZ3hrvtOLqVVaevPpxeTnOZwf978BQ4BJQJ+adlLVEhGZAizBSSp/VtVNIvIIsFpVFwA/BF4UkftwGqxvUXV+nUVkD04DdpyIjAdGVuoBVW/RIgGTQXQQGsxUlR+/tYFPs4/y0qQh9G5vw2g0RSljx5KY7VTx9X4p/PeTbl95kEOfHaW0RHnlfz5k2Lie9BnaoeYdG5HWSXHlY1D5FJaUsvPwifLG8M05R1m8Mae8R6IIdG3Twrna6HC6iiojyIMY9hs+gozNzr//5DvvCNpxGwpPKVZVd4pItKqWAn8RkSzgIQ/7LcbpuupfNs3v9Wbgkir27eYltvqYOLRzhTYI//L6+sOyXSxcn82PR/flqn51HEbDmGpsX3mQpa9tpTTO+SPnxJeFLH1tK0CTSxKVxcdEc3ZmCmdnpsD5Tpmqkn20gC3Zp7vfbso+xuKNB8v3S20RWyFh9M9Iple7ljaIYRW8JIiTIhIHrBORx3EarpvEp+lrZ/AliWiRoPRi+ufmQzyxZBvXnZvJ9y/vWe84jQlkxfxdlBSVVZjnsaSojBXzdzX5BBGIiNAxNZGOqYl8zW9ss+MFxWw7ePx0NVX2Mf768V4KS04PYtirXSu3TaNVeW8qqxL2liC+i1NFNAW4D6fh+RuhDCqcfjH+HHYccibJC8aNctsPHWfq7CwGZKbw+DcHNvj+3Yt2L2JD7n6KyooY+eb/MnXwVMb0GBPpsIwHJ74srFV5c9UqIZYh3dpUuPeopLSMPV/ks9mtotqSc4wPduTy1trT92xkpiRUuF+jX0YyXZrZIIZeBuvb6748hTOqq6lC3ski7nh1NYlxMcyYdH6D78e9aPcipn80naIyp9dFTn4O0z+aDmBJohFo2SY+YDJo2abhdAVtqGKio+jVrhW92rUKOIihf/fbQIMY+ne/LS3TiPSiCofqbpTbSIBB+nxUdWBIImqkSkrLuOv1teTkFTBr8kVkpIR+RNj6embtMxSUVrwTuKC0gGfWPmMJohEYNq5neZuDT0xcFMPGWbVmXVU1iOH2Q8f9ut8e5+2sA8z8eG/5Nq0SYnh/22Eu75Pe4GsNaqO6K4ivu893uc/+EwYFpx9oE/KLRVv4cOcX/OZb53J+19Y17xAs9ZgP4mD+wVqVm4bF184w6+11lJYoLdvEN8leTJGWEBvNwE6pDOyUWl5WVuYMYrg55xiP/H0TR44XcctfVjGgYzJ3XdGLUWd3CEtVVH7WYYo+P46WlpHz609IHtWNpEHtat7Royobm1V1r1u9dLWq/lhVN7qPnwAjgxZBE/DGqs95+aM93HZpd755fhgHyiufD8KtZvDNB7FhjqfdOyQF/iGpqtw0PH2GdqB99xQye6dy868useQQJlFRQpe2zgCGnVu34NzOKTz+jYHkF5by/dfWcvVTy3hzzX6KSz0NClEn+VmHyZu7A3XPUZpXSN7cHeRnBe8+Yy+9kURELvFbuNjjfs3C6j1f8vC8TxneO42HrjkrvCevbj4ID6YOnkpCdEKFsoToBKYOnhqsCI1pFqJEuPGCzvzz/sv53cRBxEZH8aO/reeKJ95n5oo9FFSa2jgYji3ZgxZXTEBaXMaxJXuCdg4vP/S3Ab8XkT0ishf4PU1kytH6OpB3iu/9dQ2dWrfguYmDwz+MRj3ngxjTYwzjeo0rX46SKMb1GmftD7XgzAexnpOrVrHjyqs4unBhpEMyERQdJYw9N5N3pg7nz7cMoX1yPD+bv4lLH1vKC8t2caKwJGjnKs0L3FutqvK6qPEXTVXXqOq5wLnAQFU9T1XXBi2CRupkUQl3vLKawuIyXpw0hJQWERjnvqp5HzzOB7Fo9yLm75xfvlymZczfOZ9FuxcFI7omr3w+iKIi4PR8EJYkjIhw5Vnteev7FzPrjovol9GKR9/ZyiW//jdPvredr/KL6n2O6NTAvdWqKq+LKhOEiNzkPt8vIvfjXEnc5rfcbKkqD/xtA1sOHuPZiYPo1a5lZAK5apoz/4O/WswHUV0vJlOz6uaDMAacRDGsZ1tm3jaU+XddwkU92vDsv3ZwyWP/5peLNnPoWEHNB6lC8qhuSGzFn3CJjSJ5VLd6Rn1adb2YktxnG0SokueX7mTRxhweuuYsRpwVvB4DtVbP+SCsF1P92HwQpjZTjp7bOZUXvjuE7YeO84f3d/HnD/fwykd7+eaQTnzvsp50aduiVuf29VaSN9ehpWVEp8YHvRdTdcN9v+A+281xft7ddJDfvLud6wd1ZPJlPSIdTr3mg0iJTyGvMC9guamZzQfRvNV1ytE+7Vvx1LfP476v9eGPH+zizdX7eWPVPmdonit60qcWA3smDWpH3CfO9hl3XliPdxNYdTfKPVvdjqoa/qErI2zbwePc98Y6zu2UwqM3nNPob4jRKoY1r6rcVGTzQTRv9Z1ytEvbFvzq+nOYelVvXlq+m9dWfs7bWQcYdXZ77hrRq8J9F5FSXRXTmrBF0Qh8lV/E7a+uIik+hhe+O6TBD6PhxbGiY7UqNxXZfBDNW7CmHG2fnMBPx/TnB1f04i8f7eHlDz9jyaZDDO+dxl0jejG0e5uI/TFaXRXTK+EMpCErLi3jB6+t5dCxQt6YfBEdUhJq3qkR6JDUgZz8M+vL7UY5Y2oW7ClHWyfFcf/VfZh8WQ9e+3gvLy7/jAkzPub8rq25a0RPRvRtF/ZE4WVGuXTgJ0B/nBnfAFDVK0MYV4Pyf3/fzIrdX/DkjedWmCKxsZs6eCrTP5rOSb8yu1HOO18318fcnkwlUF7lZFcRTV+ophxtGR/DnZf35OaLu/G31fv447Ld/PfLq+mXkcxdI3pyzYCMsA0O6OXOrteALUB3nNFc9+BMJ9osvL7yc15dsZfJl/XghsFhHEYjDMb0GMP0i6cTF+WMe5+RlMH0i6fbjXIeWTfX5q3f8BGMnDyF6Ng4EKFVWjojJ08J2pSjCbHRfHdYN95/4Ap++61zKSopZcrrWXztyWXMWbWPopLQDePh42U+iLaq+icRmaqqy4BlItIsEsTK3V8wbf6nXN4nnZ+MDvMwGmEypscYXk13ekG98c27IxxN49IQurkue30r2TvyAPj9D/7N2Zdmcvl3muZ3tSEKx5SjsdFRfOP8Towf1JF3Nx3kuaU7+fFbG3j6n9uZfFmPkA437iVBFLvPOSIyBsgG2lSzfZOw/6uTfP+1tXRp24JnJw5qsuO9m7qLdDfXZa9v5dMPssG9T1PLcJbBkkQTFB0lXHNOBqMHdGDZ9lx+v3QX0xduJiZKyEhJQFWD3kbhpYrpFyKSAvwQ+BHwEs7Mck3WyaISbn9lNcWl7jAaiREYRiOM3rhzWFBm02tu2t13L5JQscNCOLu5bvrPmcmpunLTNIgIV/Rtx5zvDWPOncNIio/hRGFJSBqwvVxBrFTVo8BRIDiVaw1YWZnywznr2X7oOH+59UJ6pkdoGA3T4Pkaog8/9TQlOTnEZGSEtZurVlEFXVW5aXou7N6Gszq0oixE9y55SRAfisge4A1grqp+FZJIGojf/Xsn73x6kIfH9ONyv1mlGjL76z9yUsaOjViPJYkKnAzEBuNvdqJC1P3Vy2iufYCHgbOBNSLyd99Afk3NPz7N4al/bueGwR257dLukQ7HmGqdfWlmrcqNqS1Pf2uo6ieqej9wIfAl4OkmOhEZLSLbRGSniDwYYH0XEVkqIlkiskFErvVb95C73zYRGeXx/dTZyaIS7p+znvM6p/Kr6xv/MBqm6bv8O2cx4LJMJp6MZ8KJeCQKBlxmvZhM8Hi5US4ZuB6YAPQE3sZJFDXtFw08D1wN7AdWicgCVd3st9nDwBxV/YOI9AcWA93c1xNwrloygX+KSB9VDf60TDh3Sm87dILWLWKZ8d3zm8QwGqZ5uPw7Z1lCMCHjpQ1iPTAPeERVV9Ti2BcCO1V1N4CIzAbGAf4JQoFk93UKThda3O1mq2oh8JmI7HSPV5vze1JcWsaOwycoLi1jxneH0C65aQyjYYwx9eWliqmHqt6nqitE5Ou1OHZHYJ/f8n63zN904CYR2Y9z9eC7U8vLvojIZBFZLSKrc3PPHBPFi+y8UxQUl9IjLYlzO6fW6RgRtWEOPDUApqc6zxvmRDoiY0yY5Gcdpujz4xR+dpScX39CftbhoB7fSyO1f/+pR4J6dpgIvKyqnYBrgZki3vtgqOoMVR2iqkPS0+vW46hr2yTO7ZRKWsvgTdMXNhvmwMJ74Og+QJ3nhfdYkjCmGcjPOkze3B1oqdOVrTSvkLy5O4KaJGrbIa42LbcHgM5+y53cMn+3AXMA3OqrBCDN475B02jvkv7XI1B8qmJZ8Smn3BjTpB1bsgctrtjPWYvLOLZkT9DOUdsEcWcttl0F9BaR7iISh9PovKDSNp8DVwGISD+cBJHrbjdBROJFpDvQG/iklrE2fUf3167cGNNklOYV1qq8LmpMECLyLRHxzYE3SkTmisjgmvZT1RJgCrAEZzTYOaq6SUQeEZHr3M1+CNwhIuuBWcAt6tiEc2WxGfgHcFeoejA1ailVjC5bVbkxJqicOam3sX/Lp8y461a2LF8atnNHpwauFq+qvC68XEH8TFWPi8ilwJXAn4A/eDm4qi5W1T6q2lNVf+mWTVPVBe7rzap6iaqeq6rnqeq7fvv+0t2vr6q+U/u31gxcNQ1iEyuWxSY65caYkCqfk7q4CFTL56QOV5JIHtUNia34Ey6xUSSP6ha0c3hJEL6/3McAL6rqIiAuaBGYuht4I4x9FlI6A+I8j33WKTfGhFR1c1KHQ9KgdqTe0BuJdn7Go1PjSb2hN0mD2gXtHF7ugzggIi/g3PD2mIjEU/u2CxMqA2+0hGBMBARrTuqGzMsP/Y047QijVDUPZy6IB0IZlDHGNHRVzT1d1zmpa6uhdHPNABap6g4RuQL4FtajyBjTzA2fMImYuIoNwsGYk9qrhtLN9S2gVER6ATNw7k94PWgRGGNMIxTqOalrEo5url7aIMpUtUREbgB+p6q/E5GsoEVgjDGNVDjmpK5KdGp8wGQQ7m6uxSIyEZgE/N0ta9pzcBpjTAPXULq53goMA36pqp+5dzbPDFoExhhjaq1BdHNV1c0i8iOgj4gMALap6mNBi8AYY0ydJA1qR9wnzkAXGXfWOE1PrXmZMOgKnBnk9uAM1tdZRG5W1Q+CHo0xxpgGw0sj9W+Bkaq6DUBE+uCMm3R+KAMzxhgTWV7aIGJ9yQFAVbdjjdTGGNPkebmCWCMiLwF/dZf/C1gdupCMMcY0BF4SxPeAu4B73OXlwO9DFpExxpgGodoEISLRwHpVPQt4MjwhGWOMaQiqbYNwJ+nZJiJdwhSPMcaYBsJLFVNrYJOIfALk+wpV9bqqdzHGmObhjTuHRTqEkPGSIH4W8iiMMcY0OFUmCHf01vaquqxS+aVATqgDM8YYE1nVtUE8DRwLUH7UXWeMMaYJq66Kqb2qbqxcqKobRaRb6EIyxpjGYcvypSyf/SrHvzhCq7ZpDJ8wKWzzQYRDdQkitZp1iUGOwxhjGpUty5fy7oznKCly5mQ4fiSXd2c8B9BkkkR1VUyrReSMGTBE5HZgTehCMsaYhm/57FfLk4NPSVEhy2e/GqGIgq+6BHEvcKuIvC8iv3Ufy4DbgKleDi4io0Vkm4jsFJEHA6x/SkTWuY/tIpLnt+4xEfnUfXy7dm/Lu3lZB8j6PI+Vn33JJb/+N/OyDoTqVMaYJuT4F0dqVd4YVVnFpKqHgItFZAQwwC1epKr/9nJg9y7s54Grgf3AKhFZoKqb/c5xn9/2dwOD3NdjgMHAeUA88L6IvKOqgRrN62xe1gEemruRolJn4u8Dead4aK7T7DJ+UMdgnsoY08S0apvG8SO5AcvDKZT3YdQ4mquqLlXV37kPT8nBdSGwU1V3q2oRMBsYV832E3GGEQfoD3ygqiWqmg9sAEbX4tyePLFkG6eKSyuUnSou5Ykl26rYwxhjHMMnTCImruL8zzFx8QyfMClCEQWfl+G+66ojsM9veb9bdgYR6Qp0B3wJaD0wWkRaiEgaMALoHGC/ySKyWkRW5+aemclrkp13qlblxhjj02/4CEZOnkKrtHQQoVVaOiMnT2kyDdTg7U7qcJgAvOmO/YSqvisiFwAfAbnACqC08k6qOgOYATBkyBCt7UkzUxM5ECAZZKZaJy1jTM36DR/RpBJCZaG8gjhAxb/6O7llgUzgdPUSAKr6S1U9T1WvxpnqdHuwA3xgVF8SY6MrlCXGRvPAqL7BPpUxxjQ6oUwQq4DeItJdROJwksCCyhuJyFk4AwKu8CuLFpG27uuBwEDg3WAHOH5QRx694Rziop2PoWNqIo/ecI41UBtjDCGsYlLVEhGZAiwBooE/q+omEXkEWK2qvmQxAZitqv5VRLHAchEBZ7iPm1S1JBRxjh/UkVmffA407VEZjTGmtkLaBqGqi4HFlcqmVVqeHmC/ApyeTMYYYyIklFVMxhhjGrGG0ovJGGNMLeVnHebYkj2U5hUSnRpP8qhuJA1qF7TjW4IwxphGKD/rMHlzd6DFzkgQpXmF5M3dARC0JGEJAmucNsY0PseW7ClPDj5aXMaxJXuCliCsDcIYYxqh0rzCWpXXhSUIY4xphKJT42tVXheWIIwxphFKHtUNia34Ey6xUSSP6ha0c1gbhDHGNEK+dgbrxWSMMeYMSYPaBTUhVGZVTMYYYwKyBGGMMSYgSxDGGGMCsgRhjDEmIEsQxhhjArIEYYwxJiBLEMYYYwKyBGGMMSYgSxDGGGMCsgRhjDEmIEsQxhhjArIEYYwxJiBLEMYYYwKyBGGMMSagkA73LSKjgWeAaOAlVf11pfVPASPcxRZAO1VNddc9DozBSWLvAVNVVYMd47ysAzyxZBvZeafITE3kgVF9GT+oY7BPY4wxjU7IEoSIRAPPA1cD+4FVIrJAVTf7tlHV+/y2vxsY5L6+GLgEGOiu/g9wOfB+MGOcl3WAh+Zu5FRxKQAH8k7x0NyNAJYkjDHNXiirmC4EdqrqblUtAmYD46rZfiIwy32tQAIQB8QDscChYAf4xJJt5cnB51RxKU8s2RbsUxljTKMTygTREdjnt7zfLTuDiHQFugP/BlDVFcBSIMd9LFHVLQH2mywiq0VkdW5ubq0DzM47VatyY4xpThpKI/UE4E1VLQUQkV5AP6ATTlK5UkSGV95JVWeo6hBVHZKenl7rk2amJtaq3BhjmpNQJogDQGe/5U5uWSATOF29BHA98LGqnlDVE8A7wLBgB/jAqL4kxkZXKEuMjeaBUX2DfSpjjGl0QpkgVgG9RaS7iMThJIEFlTcSkbOA1sAKv+LPgctFJEZEYnEaqM+oYqqv8YM68ugN59AxNREBOqYm8ugN51gDtTHGEMJeTKpaIiJTgCU43Vz/rKqbROQRYLWq+pLFBGB2pS6sbwJXAhtxGqz/oaoLQxHn+EEdLSEYY0wAEoJbCyJiyJAhunr16kiHYYwxjYqIrFHVIYHWNZRGamOMMQ2MJQhjjDEBWYIwxhgTkCUIY4wxATWZRmoRyQX2RjqOaqQBRyIdRDUsvvqx+OrH4quf+sTXVVUD3mncZBJEQyciq6vqKdAQWHz1Y/HVj8VXP6GKz6qYjDHGBGQJwhhjTECWIMJnRqQDqIHFVz8WX/1YfPUTkvisDcIYY0xAdgVhjDEmIEsQxhhjArIEESQi0llElorIZhHZJCJTA2xzhYgcFZF17mNaBOLcIyIb3fOfMbqhOJ4VkZ0iskFEBocxtr5+n806ETkmIvdW2iasn6GI/FlEDovIp35lbUTkPRHZ4T63rmLfm91tdojIzWGM7wkR2er++70tIqlV7FvtdyGE8U0XkQN+/4bXVrHvaBHZ5n4XHwxjfG/4xbZHRNZVsW84Pr+Avyth+w6qqj2C8AAygMHu61bAdqB/pW2uAP4e4Tj3AGnVrL8WZ4ImAS4CVkYozmjgIM5NPBH7DIHLgMHAp35ljwMPuq8fBB4LsF8bYLf73Np93TpM8Y0EYtzXjwWKz8t3IYTxTQd+5OHffxfQA2du+vWV/z+FKr5K638LTIvg5xfwdyVc30G7gggSVc1R1bXu6+M4Exw1xokmxgGvquNjIFVEMiIQx1XALlWN6N3xqvoB8GWl4nHAK+7rV4DxAXYdBbynql+q6lfAe8DocMSnqu+qaom7+DHObI4RUcXn58WFwE5V3a2qRcBsnM89qKqLT0QEuJGKs12GVTW/K2H5DlqCCAER6QYMAlYGWD1MRNaLyDsicnZ4IwOcCZjeFZE1IjI5wPqOwD6/5f1EJtFVnobWX6Q/w/aqmuO+Pgi0D7BNQ/kc/xvnijCQmr4LoTTFrQL7cxXVIw3h8xsOHFLVHVWsD+vnV+l3JSzfQUsQQSYiLYG3gHtV9Vil1WtxqkzOBX4HzAtzeACXqupg4BrgLhG5LAIxVEucKWqvA/4WYHVD+AzLqXMt3yD7iovIT4ES4LUqNonUd+EPQE/gPCAHpxqnIZpI9VcPYfv8qvtdCeV30BJEEIkzf/ZbwGuqOrfyelU9pqon3NeLgVgRSQtnjKp6wH0+DLyNcynv7wDQ2W+5k1sWTtcAa1X1UOUVDeEzBA75qt3c58MBtono5ygitwBfB/7L/QE5g4fvQkio6iFVLVXVMuDFKs4b6c8vBrgBeKOqbcL1+VXxuxKW76AliCBx6yv/BGxR1Ser2KaDux0iciHO5/9FGGNMEpFWvtc4jZmfVtpsATBJHBcBR/0uZcOlyr/cIv0ZuhYAvh4hNwPzA2yzBBgpIq3dKpSRblnIicho4MfAdap6soptvHwXQhWff5vW9VWcdxXQW0S6u1eUE3A+93D5GrBVVfcHWhmuz6+a35XwfAdD2QLfnB7ApTiXeRuAde7jWuB7wPfcbaYAm3B6ZHwMXBzmGHu4517vxvFTt9w/RgGex+lBshEYEuYYk3B+8FP8yiL2GeIkqhygGKcO9zagLfAvYAfwT6CNu+0Q4CW/ff8b2Ok+bg1jfDtx6p5938M/uttmAour+y6EKb6Z7ndrA84PXUbl+Nzla3F67ewKZ3xu+cu+75zftpH4/Kr6XQnLd9CG2jDGGBOQVTEZY4wJyBKEMcaYgCxBGGOMCcgShDHGmIAsQRhjjAnIEoQxISQi3fxHCjWmMbEEYYwxJiBLEMaEiYj0EJEsEbkg0rEY40VMpAMwpjkQkb44Q1bfoqrrIx2PMV5YgjAm9NJxxsq5QVU3RzoYY7yyKiZjQu8o8DnOuDrGNBp2BWFM6BXhjFq6REROqOrrkQ7IGC8sQRgTBqqaLyJfB95zk0Q4h642pk5sNFdjjDEBWRuEMcaYgCxBGGOMCcgShDHGmIAsQRhjjAnIEoQxxpiALEEYY4wJyBKEMcaYgP4fg+Re4hjKzmcAAAAASUVORK5CYII=\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "# plot the raw observations\n",
     "for k in k_choices:\n",
@@ -1156,9 +1241,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 35,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Got 399 / 500 correct => accuracy: 0.798000\n"
+     ]
+    }
+   ],
    "source": [
     "X_train =X_train/255\n",
     "X_test = X_test/255\n",
@@ -1188,7 +1281,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 36,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1293,7 +1386,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 37,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1303,9 +1396,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 38,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(500, 5000)"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "dists = classifier.compute_distances_two_loops(X_test)\n",
     "dists.shape"
@@ -1313,7 +1417,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 39,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1322,9 +1426,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 40,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Got 192 / 500 correct => accuracy: 0.384000\n"
+     ]
+    }
+   ],
    "source": [
     "num_test = X_test.shape[0]\n",
     "\n",
diff --git a/notebooks/Block_2/Jupyter Notebook Block 2 - Neural Networks .ipynb b/notebooks/Block_2/Jupyter Notebook Block 2 - Neural Networks .ipynb
index 06fbf338c4e350237b325934e932fd8527fcccca..842df71fbe9a07323842ad821a33e05a5a5dbd2a 100644
--- a/notebooks/Block_2/Jupyter Notebook Block 2 - Neural Networks .ipynb	
+++ b/notebooks/Block_2/Jupyter Notebook Block 2 - Neural Networks .ipynb	
@@ -34,12 +34,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -118,15 +118,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[[-0.00398531  0.01067583 -0.00071457]\n",
-      " [ 0.01394736  0.01609133  0.01195591]]\n",
+      "[[-0.00267982 -0.00939783  0.01066554]\n",
+      " [-0.01248895  0.00193128  0.00701094]]\n",
       "[[0. 0. 0.]]\n"
      ]
     }
@@ -166,7 +166,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -250,7 +250,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -259,8 +259,8 @@
      "text": [
       "(300, 3)\n",
       "[[0.33333333 0.33333333 0.33333333]\n",
-      " [0.33333492 0.3333378  0.33332728]\n",
-      " [0.33332394 0.33336023 0.33331583]]\n"
+      " [0.33329492 0.33333342 0.33337165]\n",
+      " [0.3332603  0.3333631  0.3333766 ]]\n"
      ]
     }
    ],
@@ -298,7 +298,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -337,14 +337,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "1.0982809615383764\n"
+      "1.0992698413070723\n"
      ]
     }
    ],
@@ -428,7 +428,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -470,7 +470,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -558,33 +558,33 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "iteration 0: loss 1.100905\n",
-      "iteration 10: loss 0.908582\n",
-      "iteration 20: loss 0.836226\n",
-      "iteration 30: loss 0.802860\n",
-      "iteration 40: loss 0.785220\n",
-      "iteration 50: loss 0.775010\n",
-      "iteration 60: loss 0.768721\n",
-      "iteration 70: loss 0.764668\n",
-      "iteration 80: loss 0.761966\n",
-      "iteration 90: loss 0.760118\n",
-      "iteration 100: loss 0.758828\n",
-      "iteration 110: loss 0.757913\n",
-      "iteration 120: loss 0.757255\n",
-      "iteration 130: loss 0.756777\n",
-      "iteration 140: loss 0.756427\n",
-      "iteration 150: loss 0.756168\n",
-      "iteration 160: loss 0.755975\n",
-      "iteration 170: loss 0.755832\n",
-      "iteration 180: loss 0.755724\n",
-      "iteration 190: loss 0.755643\n"
+      "iteration 0: loss 1.096572\n",
+      "iteration 10: loss 0.907185\n",
+      "iteration 20: loss 0.836251\n",
+      "iteration 30: loss 0.803732\n",
+      "iteration 40: loss 0.786672\n",
+      "iteration 50: loss 0.776895\n",
+      "iteration 60: loss 0.770939\n",
+      "iteration 70: loss 0.767149\n",
+      "iteration 80: loss 0.764658\n",
+      "iteration 90: loss 0.762978\n",
+      "iteration 100: loss 0.761824\n",
+      "iteration 110: loss 0.761018\n",
+      "iteration 120: loss 0.760448\n",
+      "iteration 130: loss 0.760041\n",
+      "iteration 140: loss 0.759749\n",
+      "iteration 150: loss 0.759536\n",
+      "iteration 160: loss 0.759382\n",
+      "iteration 170: loss 0.759268\n",
+      "iteration 180: loss 0.759185\n",
+      "iteration 190: loss 0.759123\n"
      ]
     }
    ],
@@ -644,14 +644,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "training accuracy: 0.51\n"
+      "training accuracy: 0.53\n"
      ]
     }
    ],
@@ -706,7 +706,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -727,7 +727,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
@@ -776,7 +776,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -817,7 +817,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -861,7 +861,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -878,7 +878,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -896,23 +896,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "iteration 0: loss 1.098700\n",
-      "iteration 1000: loss 0.278271\n",
-      "iteration 2000: loss 0.249424\n",
-      "iteration 3000: loss 0.247798\n",
-      "iteration 4000: loss 0.243975\n",
-      "iteration 5000: loss 0.243065\n",
-      "iteration 6000: loss 0.242337\n",
-      "iteration 7000: loss 0.241996\n",
-      "iteration 8000: loss 0.241719\n",
-      "iteration 9000: loss 0.241721\n"
+      "iteration 0: loss 1.098594\n",
+      "iteration 1000: loss 0.313787\n",
+      "iteration 2000: loss 0.262327\n",
+      "iteration 3000: loss 0.254925\n",
+      "iteration 4000: loss 0.249680\n",
+      "iteration 5000: loss 0.247624\n",
+      "iteration 6000: loss 0.246463\n",
+      "iteration 7000: loss 0.245824\n",
+      "iteration 8000: loss 0.245585\n",
+      "iteration 9000: loss 0.245514\n"
      ]
     }
    ],
@@ -985,14 +985,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "training accuracy: 0.98\n"
+      "training accuracy: 0.99\n"
      ]
     }
    ],
@@ -1058,14 +1058,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2.1.0\n"
+      "2.7.1\n"
      ]
     }
    ],
@@ -1102,7 +1102,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1131,7 +1131,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [
     {
@@ -1140,7 +1140,7 @@
        "(300, 2)"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 26,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1161,20 +1161,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Model: \"sequential\"\n",
+      "Model: \"sequential_2\"\n",
       "_________________________________________________________________\n",
-      "Layer (type)                 Output Shape              Param #   \n",
+      " Layer (type)                Output Shape              Param #   \n",
       "=================================================================\n",
-      "dense (Dense)                (None, 100)               300       \n",
-      "_________________________________________________________________\n",
-      "dense_1 (Dense)              (None, 3)                 303       \n",
+      " dense_4 (Dense)             (None, 100)               300       \n",
+      "                                                                 \n",
+      " dense_5 (Dense)             (None, 3)                 303       \n",
+      "                                                                 \n",
       "=================================================================\n",
       "Total params: 603\n",
       "Trainable params: 603\n",
@@ -1202,7 +1203,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [
     {
@@ -1239,7 +1240,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [
     {
@@ -1260,2023 +1261,2022 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Train on 300 samples\n",
       "Epoch 1/1000\n",
-      "300/300 [==============================] - 0s 1ms/sample - loss: 1.0951 - accuracy: 0.1900\n",
+      "3/3 [==============================] - 1s 3ms/step - loss: 1.0828 - accuracy: 0.3133\n",
       "Epoch 2/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 1.0815 - accuracy: 0.2967\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 1.0702 - accuracy: 0.3733\n",
       "Epoch 3/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 1.0683 - accuracy: 0.3867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 1.0585 - accuracy: 0.4300\n",
       "Epoch 4/1000\n",
-      "300/300 [==============================] - 0s 41us/sample - loss: 1.0555 - accuracy: 0.4033\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 1.0472 - accuracy: 0.5100\n",
       "Epoch 5/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 1.0433 - accuracy: 0.4833\n",
+      "3/3 [==============================] - 0s 16ms/step - loss: 1.0359 - accuracy: 0.5367\n",
       "Epoch 6/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 1.0314 - accuracy: 0.5233\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 1.0246 - accuracy: 0.5500\n",
       "Epoch 7/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 1.0199 - accuracy: 0.5333\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 1.0135 - accuracy: 0.5533\n",
       "Epoch 8/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 1.0083 - accuracy: 0.5633\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 1.0028 - accuracy: 0.5600\n",
       "Epoch 9/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.9973 - accuracy: 0.5767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.9918 - accuracy: 0.5500\n",
       "Epoch 10/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.9869 - accuracy: 0.5900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.9819 - accuracy: 0.5500\n",
       "Epoch 11/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.9758 - accuracy: 0.5967\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.9713 - accuracy: 0.5533\n",
       "Epoch 12/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.9656 - accuracy: 0.5967\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.9609 - accuracy: 0.5533\n",
       "Epoch 13/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.9558 - accuracy: 0.5967\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.9512 - accuracy: 0.5533\n",
       "Epoch 14/1000\n",
-      "300/300 [==============================] - 0s 39us/sample - loss: 0.9459 - accuracy: 0.6033\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.9410 - accuracy: 0.5533\n",
       "Epoch 15/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.9362 - accuracy: 0.6033\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.9311 - accuracy: 0.5533\n",
       "Epoch 16/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.9269 - accuracy: 0.6000\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.9219 - accuracy: 0.5500\n",
       "Epoch 17/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.9178 - accuracy: 0.5967\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.9123 - accuracy: 0.5533\n",
       "Epoch 18/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.9088 - accuracy: 0.5867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.9033 - accuracy: 0.5500\n",
       "Epoch 19/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.8998 - accuracy: 0.5767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.8944 - accuracy: 0.5533\n",
       "Epoch 20/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.8912 - accuracy: 0.5800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.8854 - accuracy: 0.5533\n",
       "Epoch 21/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.8823 - accuracy: 0.5800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.8767 - accuracy: 0.5533\n",
       "Epoch 22/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.8740 - accuracy: 0.5733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.8686 - accuracy: 0.5533\n",
       "Epoch 23/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.8657 - accuracy: 0.5733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.8600 - accuracy: 0.5533\n",
       "Epoch 24/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.8575 - accuracy: 0.5733\n",
+      "3/3 [==============================] - 0s 7ms/step - loss: 0.8524 - accuracy: 0.5533\n",
       "Epoch 25/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.8498 - accuracy: 0.5600\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.8446 - accuracy: 0.5533\n",
       "Epoch 26/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.8418 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.8372 - accuracy: 0.5533\n",
       "Epoch 27/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.8343 - accuracy: 0.5567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.8299 - accuracy: 0.5500\n",
       "Epoch 28/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.8268 - accuracy: 0.5600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.8230 - accuracy: 0.5500\n",
       "Epoch 29/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.8193 - accuracy: 0.5600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.8165 - accuracy: 0.5500\n",
       "Epoch 30/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.8123 - accuracy: 0.5600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.8102 - accuracy: 0.5500\n",
       "Epoch 31/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.8054 - accuracy: 0.5567\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.8041 - accuracy: 0.5533\n",
       "Epoch 32/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.7986 - accuracy: 0.5633\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.7979 - accuracy: 0.5533\n",
       "Epoch 33/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.7923 - accuracy: 0.5567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7924 - accuracy: 0.5533\n",
       "Epoch 34/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.7860 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7870 - accuracy: 0.5533\n",
       "Epoch 35/1000\n",
-      "300/300 [==============================] - 0s 40us/sample - loss: 0.7799 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7817 - accuracy: 0.5533\n",
       "Epoch 36/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.7741 - accuracy: 0.5500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7769 - accuracy: 0.5500\n",
       "Epoch 37/1000\n",
-      "300/300 [==============================] - 0s 40us/sample - loss: 0.7685 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7721 - accuracy: 0.5500\n",
       "Epoch 38/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.7630 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7673 - accuracy: 0.5533\n",
       "Epoch 39/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.7579 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7627 - accuracy: 0.5500\n",
       "Epoch 40/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.7528 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.7585 - accuracy: 0.5500\n",
       "Epoch 41/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.7479 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7545 - accuracy: 0.5533\n",
       "Epoch 42/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.7431 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7504 - accuracy: 0.5567\n",
       "Epoch 43/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.7386 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7466 - accuracy: 0.5567\n",
       "Epoch 44/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.7341 - accuracy: 0.5567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7430 - accuracy: 0.5600\n",
       "Epoch 45/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.7298 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7392 - accuracy: 0.5600\n",
       "Epoch 46/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.7257 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7359 - accuracy: 0.5600\n",
       "Epoch 47/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.7216 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.7324 - accuracy: 0.5600\n",
       "Epoch 48/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.7177 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.7291 - accuracy: 0.5600\n",
       "Epoch 49/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.7139 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.7259 - accuracy: 0.5633\n",
       "Epoch 50/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.7100 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.7229 - accuracy: 0.5633\n",
       "Epoch 51/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.7065 - accuracy: 0.5533\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.7198 - accuracy: 0.5633\n",
       "Epoch 52/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.7030 - accuracy: 0.5567\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.7170 - accuracy: 0.5667\n",
       "Epoch 53/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.6994 - accuracy: 0.5567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7141 - accuracy: 0.5700\n",
       "Epoch 54/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.6959 - accuracy: 0.5600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7113 - accuracy: 0.5733\n",
       "Epoch 55/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.6927 - accuracy: 0.5633\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.7084 - accuracy: 0.5733\n",
       "Epoch 56/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.6893 - accuracy: 0.5633\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.7059 - accuracy: 0.5733\n",
       "Epoch 57/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.6861 - accuracy: 0.5633\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7032 - accuracy: 0.5733\n",
       "Epoch 58/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.6830 - accuracy: 0.5667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.7005 - accuracy: 0.5733\n",
       "Epoch 59/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.6800 - accuracy: 0.5667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6979 - accuracy: 0.5700\n",
       "Epoch 60/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.6768 - accuracy: 0.5700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6956 - accuracy: 0.5700\n",
       "Epoch 61/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.6739 - accuracy: 0.5700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6930 - accuracy: 0.5733\n",
       "Epoch 62/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.6709 - accuracy: 0.5700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6904 - accuracy: 0.5733\n",
       "Epoch 63/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.6679 - accuracy: 0.5700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6880 - accuracy: 0.5733\n",
       "Epoch 64/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.6651 - accuracy: 0.5700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6856 - accuracy: 0.5733\n",
       "Epoch 65/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.6623 - accuracy: 0.5700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6834 - accuracy: 0.5733\n",
       "Epoch 66/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.6595 - accuracy: 0.5700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6809 - accuracy: 0.5733\n",
       "Epoch 67/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.6565 - accuracy: 0.5733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6787 - accuracy: 0.5733\n",
       "Epoch 68/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.6538 - accuracy: 0.5833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6762 - accuracy: 0.5733\n",
       "Epoch 69/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.6511 - accuracy: 0.5833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6741 - accuracy: 0.5733\n",
       "Epoch 70/1000\n",
-      "300/300 [==============================] - 0s 38us/sample - loss: 0.6484 - accuracy: 0.5867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6716 - accuracy: 0.5800\n",
       "Epoch 71/1000\n",
-      "300/300 [==============================] - 0s 51us/sample - loss: 0.6456 - accuracy: 0.5900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6694 - accuracy: 0.5800\n",
       "Epoch 72/1000\n",
-      "300/300 [==============================] - ETA: 0s - loss: 0.5909 - accuracy: 0.66 - 0s 36us/sample - loss: 0.6429 - accuracy: 0.5900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6673 - accuracy: 0.5833\n",
       "Epoch 73/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.6403 - accuracy: 0.5900\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.6650 - accuracy: 0.5833\n",
       "Epoch 74/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.6377 - accuracy: 0.5900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6627 - accuracy: 0.5833\n",
       "Epoch 75/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.6350 - accuracy: 0.5900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6605 - accuracy: 0.5867\n",
       "Epoch 76/1000\n",
-      "300/300 [==============================] - 0s 38us/sample - loss: 0.6326 - accuracy: 0.5900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6584 - accuracy: 0.5833\n",
       "Epoch 77/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.6297 - accuracy: 0.6000\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6561 - accuracy: 0.5900\n",
       "Epoch 78/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.6271 - accuracy: 0.5967\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6541 - accuracy: 0.5867\n",
       "Epoch 79/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.6248 - accuracy: 0.5967\n",
+      "3/3 [==============================] - 0s 7ms/step - loss: 0.6517 - accuracy: 0.5900\n",
       "Epoch 80/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.6221 - accuracy: 0.6033\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6496 - accuracy: 0.5933\n",
       "Epoch 81/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.6196 - accuracy: 0.6167\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6473 - accuracy: 0.5967\n",
       "Epoch 82/1000\n",
-      "300/300 [==============================] - 0s 40us/sample - loss: 0.6169 - accuracy: 0.6167\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6453 - accuracy: 0.5967\n",
       "Epoch 83/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.6144 - accuracy: 0.6167\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6430 - accuracy: 0.5967\n",
       "Epoch 84/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.6119 - accuracy: 0.6167\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6409 - accuracy: 0.5967\n",
       "Epoch 85/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.6094 - accuracy: 0.6167\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6388 - accuracy: 0.5967\n",
       "Epoch 86/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.6068 - accuracy: 0.6233\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6366 - accuracy: 0.5967\n",
       "Epoch 87/1000\n",
-      "300/300 [==============================] - 0s 39us/sample - loss: 0.6043 - accuracy: 0.6267\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6344 - accuracy: 0.6000\n",
       "Epoch 88/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.6019 - accuracy: 0.6300\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6325 - accuracy: 0.6000\n",
       "Epoch 89/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.5995 - accuracy: 0.6300\n",
+      "3/3 [==============================] - 0s 6ms/step - loss: 0.6301 - accuracy: 0.6000\n",
       "Epoch 90/1000\n",
-      "300/300 [==============================] - 0s 48us/sample - loss: 0.5969 - accuracy: 0.6300\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6279 - accuracy: 0.6033\n",
       "Epoch 91/1000\n",
-      "300/300 [==============================] - 0s 39us/sample - loss: 0.5943 - accuracy: 0.6300\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6259 - accuracy: 0.6033\n",
       "Epoch 92/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.5918 - accuracy: 0.6333\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6236 - accuracy: 0.6067\n",
       "Epoch 93/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.5895 - accuracy: 0.6367\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6216 - accuracy: 0.6133\n",
       "Epoch 94/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.5868 - accuracy: 0.6367\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6194 - accuracy: 0.6133\n",
       "Epoch 95/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.5843 - accuracy: 0.6500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6173 - accuracy: 0.6167\n",
       "Epoch 96/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.5818 - accuracy: 0.6500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6150 - accuracy: 0.6233\n",
       "Epoch 97/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.5793 - accuracy: 0.6567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6129 - accuracy: 0.6300\n",
       "Epoch 98/1000\n",
-      "300/300 [==============================] - 0s 39us/sample - loss: 0.5768 - accuracy: 0.6600\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6107 - accuracy: 0.6300\n",
       "Epoch 99/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.5743 - accuracy: 0.6633\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6087 - accuracy: 0.6333\n",
       "Epoch 100/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.5719 - accuracy: 0.6633\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6064 - accuracy: 0.6367\n",
       "Epoch 101/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.5693 - accuracy: 0.6633\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6044 - accuracy: 0.6367\n",
       "Epoch 102/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.5669 - accuracy: 0.6667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.6022 - accuracy: 0.6400\n",
       "Epoch 103/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.5644 - accuracy: 0.6700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.6000 - accuracy: 0.6433\n",
       "Epoch 104/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.5619 - accuracy: 0.6733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5979 - accuracy: 0.6433\n",
       "Epoch 105/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.5594 - accuracy: 0.6733\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.5957 - accuracy: 0.6433\n",
       "Epoch 106/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.5568 - accuracy: 0.6833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5937 - accuracy: 0.6500\n",
       "Epoch 107/1000\n",
-      "300/300 [==============================] - ETA: 0s - loss: 0.5137 - accuracy: 0.74 - 0s 31us/sample - loss: 0.5544 - accuracy: 0.6833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5915 - accuracy: 0.6533\n",
       "Epoch 108/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.5518 - accuracy: 0.6833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5895 - accuracy: 0.6600\n",
       "Epoch 109/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.5494 - accuracy: 0.6900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5871 - accuracy: 0.6633\n",
       "Epoch 110/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.5468 - accuracy: 0.6900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5849 - accuracy: 0.6633\n",
       "Epoch 111/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.5444 - accuracy: 0.6900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5829 - accuracy: 0.6700\n",
       "Epoch 112/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.5419 - accuracy: 0.6900\n",
+      "3/3 [==============================] - 0s 6ms/step - loss: 0.5806 - accuracy: 0.6733\n",
       "Epoch 113/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.5394 - accuracy: 0.6900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5786 - accuracy: 0.6767\n",
       "Epoch 114/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.5368 - accuracy: 0.6967\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5767 - accuracy: 0.6800\n",
       "Epoch 115/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.5344 - accuracy: 0.7000\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5744 - accuracy: 0.6800\n",
       "Epoch 116/1000\n",
-      "300/300 [==============================] - 0s 43us/sample - loss: 0.5318 - accuracy: 0.7000\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5722 - accuracy: 0.6867\n",
       "Epoch 117/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.5293 - accuracy: 0.7067\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5701 - accuracy: 0.6867\n",
       "Epoch 118/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.5269 - accuracy: 0.7067\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5678 - accuracy: 0.6867\n",
       "Epoch 119/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.5245 - accuracy: 0.7167\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5657 - accuracy: 0.6867\n",
       "Epoch 120/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.5220 - accuracy: 0.7167\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5635 - accuracy: 0.6900\n",
       "Epoch 121/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.5196 - accuracy: 0.7167\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5615 - accuracy: 0.6900\n",
       "Epoch 122/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.5169 - accuracy: 0.7200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5593 - accuracy: 0.6900\n",
       "Epoch 123/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.5145 - accuracy: 0.7167\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5572 - accuracy: 0.6867\n",
       "Epoch 124/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.5120 - accuracy: 0.7267\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5551 - accuracy: 0.6867\n",
       "Epoch 125/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.5095 - accuracy: 0.7267\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5528 - accuracy: 0.6900\n",
       "Epoch 126/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.5072 - accuracy: 0.7300\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5506 - accuracy: 0.6900\n",
       "Epoch 127/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.5047 - accuracy: 0.7367\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5485 - accuracy: 0.6900\n",
       "Epoch 128/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.5023 - accuracy: 0.7367\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5465 - accuracy: 0.6967\n",
       "Epoch 129/1000\n",
-      "300/300 [==============================] - 0s 43us/sample - loss: 0.4998 - accuracy: 0.7367\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5442 - accuracy: 0.7000\n",
       "Epoch 130/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.4973 - accuracy: 0.7400\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5421 - accuracy: 0.7000\n",
       "Epoch 131/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.4949 - accuracy: 0.7400\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5399 - accuracy: 0.7033\n",
       "Epoch 132/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.4924 - accuracy: 0.7433\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5378 - accuracy: 0.7067\n",
       "Epoch 133/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.4900 - accuracy: 0.7467\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5357 - accuracy: 0.7067\n",
       "Epoch 134/1000\n",
-      "300/300 [==============================] - 0s 38us/sample - loss: 0.4876 - accuracy: 0.7467\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5336 - accuracy: 0.7067\n",
       "Epoch 135/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.4851 - accuracy: 0.7467\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5314 - accuracy: 0.7067\n",
       "Epoch 136/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.4828 - accuracy: 0.7500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5295 - accuracy: 0.7067\n",
       "Epoch 137/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.4803 - accuracy: 0.7500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5271 - accuracy: 0.7100\n",
       "Epoch 138/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.4780 - accuracy: 0.7533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5249 - accuracy: 0.7100\n",
       "Epoch 139/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.4757 - accuracy: 0.7533\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5231 - accuracy: 0.7100\n",
       "Epoch 140/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.4732 - accuracy: 0.7567\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5208 - accuracy: 0.7133\n",
       "Epoch 141/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.4711 - accuracy: 0.7533\n",
+      "3/3 [==============================] - ETA: 0s - loss: 0.5236 - accuracy: 0.72 - 0s 3ms/step - loss: 0.5185 - accuracy: 0.7133\n",
       "Epoch 142/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.4685 - accuracy: 0.7567\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5164 - accuracy: 0.7133\n",
       "Epoch 143/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.4661 - accuracy: 0.7567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5143 - accuracy: 0.7133\n",
       "Epoch 144/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.4640 - accuracy: 0.7600\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5120 - accuracy: 0.7133\n",
       "Epoch 145/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.4615 - accuracy: 0.7633\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5102 - accuracy: 0.7167\n",
       "Epoch 146/1000\n",
-      "300/300 [==============================] - 0s 41us/sample - loss: 0.4593 - accuracy: 0.7667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5079 - accuracy: 0.7167\n",
       "Epoch 147/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.4570 - accuracy: 0.7700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5058 - accuracy: 0.7233\n",
       "Epoch 148/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.4546 - accuracy: 0.7700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.5037 - accuracy: 0.7233\n",
       "Epoch 149/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.4523 - accuracy: 0.7733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.5017 - accuracy: 0.7233\n",
       "Epoch 150/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.4501 - accuracy: 0.7733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4995 - accuracy: 0.7200\n",
       "Epoch 151/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.4478 - accuracy: 0.7733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4974 - accuracy: 0.7233\n",
       "Epoch 152/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.4454 - accuracy: 0.7800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4953 - accuracy: 0.7233\n",
       "Epoch 153/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.4432 - accuracy: 0.7800\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4933 - accuracy: 0.7233\n",
       "Epoch 154/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.4409 - accuracy: 0.7800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4913 - accuracy: 0.7300\n",
       "Epoch 155/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.4386 - accuracy: 0.7833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4892 - accuracy: 0.7333\n",
       "Epoch 156/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.4365 - accuracy: 0.7833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4871 - accuracy: 0.7333\n",
       "Epoch 157/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.4342 - accuracy: 0.7833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4850 - accuracy: 0.7333\n",
       "Epoch 158/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.4321 - accuracy: 0.7833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4831 - accuracy: 0.7367\n",
       "Epoch 159/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.4300 - accuracy: 0.7900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4810 - accuracy: 0.7433\n",
       "Epoch 160/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.4277 - accuracy: 0.7900\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.4789 - accuracy: 0.7400\n",
       "Epoch 161/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.4255 - accuracy: 0.7900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4768 - accuracy: 0.7433\n",
       "Epoch 162/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.4235 - accuracy: 0.7900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4751 - accuracy: 0.7433\n",
       "Epoch 163/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.4213 - accuracy: 0.7900\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.4729 - accuracy: 0.7433\n",
       "Epoch 164/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.4191 - accuracy: 0.7900\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.4710 - accuracy: 0.7467\n",
       "Epoch 165/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.4169 - accuracy: 0.7933\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4688 - accuracy: 0.7467\n",
       "Epoch 166/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.4148 - accuracy: 0.7967\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4669 - accuracy: 0.7500\n",
       "Epoch 167/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.4128 - accuracy: 0.7967\n",
+      "3/3 [==============================] - 0s 11ms/step - loss: 0.4649 - accuracy: 0.7500\n",
       "Epoch 168/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.4106 - accuracy: 0.7967\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4629 - accuracy: 0.7500\n",
       "Epoch 169/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.4086 - accuracy: 0.8000\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4611 - accuracy: 0.7533\n",
       "Epoch 170/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.4065 - accuracy: 0.8000\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4591 - accuracy: 0.7533\n",
       "Epoch 171/1000\n",
-      "300/300 [==============================] - 0s 38us/sample - loss: 0.4044 - accuracy: 0.8000\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4571 - accuracy: 0.7533\n",
       "Epoch 172/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.4024 - accuracy: 0.8100\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4552 - accuracy: 0.7567\n",
       "Epoch 173/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.4004 - accuracy: 0.8100\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4533 - accuracy: 0.7600\n",
       "Epoch 174/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3983 - accuracy: 0.8133\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4513 - accuracy: 0.7600\n",
       "Epoch 175/1000\n",
-      "300/300 [==============================] - 0s 40us/sample - loss: 0.3963 - accuracy: 0.8133\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4495 - accuracy: 0.7600\n",
       "Epoch 176/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.3943 - accuracy: 0.8167\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4475 - accuracy: 0.7667\n",
       "Epoch 177/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3924 - accuracy: 0.8200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4458 - accuracy: 0.7667\n",
       "Epoch 178/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3904 - accuracy: 0.8200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4437 - accuracy: 0.7667\n",
       "Epoch 179/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.3884 - accuracy: 0.8200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4421 - accuracy: 0.7667\n",
       "Epoch 180/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3864 - accuracy: 0.8200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4400 - accuracy: 0.7667\n",
       "Epoch 181/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.3845 - accuracy: 0.8233\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4382 - accuracy: 0.7767\n",
       "Epoch 182/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3825 - accuracy: 0.8233\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4363 - accuracy: 0.7733\n",
       "Epoch 183/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3807 - accuracy: 0.8300\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4345 - accuracy: 0.7767\n",
       "Epoch 184/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.3789 - accuracy: 0.8300\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4327 - accuracy: 0.7767\n",
       "Epoch 185/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.3769 - accuracy: 0.8300\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4309 - accuracy: 0.7767\n",
       "Epoch 186/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.3750 - accuracy: 0.8300\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4291 - accuracy: 0.7767\n",
       "Epoch 187/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.3731 - accuracy: 0.8333\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4272 - accuracy: 0.7767\n",
       "Epoch 188/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3713 - accuracy: 0.8333\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4254 - accuracy: 0.7767\n",
       "Epoch 189/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.3695 - accuracy: 0.8300\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4237 - accuracy: 0.7767\n",
       "Epoch 190/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.3677 - accuracy: 0.8367\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4219 - accuracy: 0.7767\n",
       "Epoch 191/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.3658 - accuracy: 0.8400\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4201 - accuracy: 0.7800\n",
       "Epoch 192/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3641 - accuracy: 0.8400\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4185 - accuracy: 0.7833\n",
       "Epoch 193/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.3623 - accuracy: 0.8400\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4166 - accuracy: 0.7833\n",
       "Epoch 194/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.3605 - accuracy: 0.8400\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4150 - accuracy: 0.7867\n",
       "Epoch 195/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.3587 - accuracy: 0.8400\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4132 - accuracy: 0.7833\n",
       "Epoch 196/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.3569 - accuracy: 0.8400\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4114 - accuracy: 0.7867\n",
       "Epoch 197/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.3553 - accuracy: 0.8500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4098 - accuracy: 0.7867\n",
       "Epoch 198/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.3535 - accuracy: 0.8600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4081 - accuracy: 0.7900\n",
       "Epoch 199/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.3518 - accuracy: 0.8600\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4064 - accuracy: 0.7933\n",
       "Epoch 200/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.3503 - accuracy: 0.8600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4047 - accuracy: 0.7933\n",
       "Epoch 201/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3484 - accuracy: 0.8600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.4031 - accuracy: 0.7933\n",
       "Epoch 202/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.3469 - accuracy: 0.8633\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.4015 - accuracy: 0.7967\n",
       "Epoch 203/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3450 - accuracy: 0.8667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3997 - accuracy: 0.7967\n",
       "Epoch 204/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3435 - accuracy: 0.8633\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3982 - accuracy: 0.7967\n",
       "Epoch 205/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.3418 - accuracy: 0.8633\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3965 - accuracy: 0.8000\n",
       "Epoch 206/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.3401 - accuracy: 0.8633\n",
+      "3/3 [==============================] - 0s 9ms/step - loss: 0.3950 - accuracy: 0.8000\n",
       "Epoch 207/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.3385 - accuracy: 0.8633\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.3933 - accuracy: 0.8000\n",
       "Epoch 208/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.3370 - accuracy: 0.8633\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3918 - accuracy: 0.8000\n",
       "Epoch 209/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.3352 - accuracy: 0.8633\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3901 - accuracy: 0.8000\n",
       "Epoch 210/1000\n",
-      "300/300 [==============================] - 0s 40us/sample - loss: 0.3339 - accuracy: 0.8633\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3886 - accuracy: 0.8000\n",
       "Epoch 211/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3322 - accuracy: 0.8733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3870 - accuracy: 0.8033\n",
       "Epoch 212/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.3305 - accuracy: 0.8767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3855 - accuracy: 0.8067\n",
       "Epoch 213/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.3291 - accuracy: 0.8733\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.3839 - accuracy: 0.8067\n",
       "Epoch 214/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.3276 - accuracy: 0.8733\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.3823 - accuracy: 0.8067\n",
       "Epoch 215/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.3260 - accuracy: 0.8767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3808 - accuracy: 0.8100\n",
       "Epoch 216/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.3245 - accuracy: 0.8767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3794 - accuracy: 0.8100\n",
       "Epoch 217/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.3230 - accuracy: 0.8767\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3778 - accuracy: 0.8133\n",
       "Epoch 218/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3214 - accuracy: 0.8767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3766 - accuracy: 0.8133\n",
       "Epoch 219/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.3201 - accuracy: 0.8800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3749 - accuracy: 0.8133\n",
       "Epoch 220/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.3186 - accuracy: 0.8767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3733 - accuracy: 0.8133\n",
       "Epoch 221/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.3171 - accuracy: 0.8767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3718 - accuracy: 0.8133\n",
       "Epoch 222/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.3157 - accuracy: 0.8767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3704 - accuracy: 0.8133\n",
       "Epoch 223/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3142 - accuracy: 0.8800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3689 - accuracy: 0.8133\n",
       "Epoch 224/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3128 - accuracy: 0.8833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3676 - accuracy: 0.8167\n",
       "Epoch 225/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3113 - accuracy: 0.8900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3661 - accuracy: 0.8167\n",
       "Epoch 226/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.3099 - accuracy: 0.8900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3647 - accuracy: 0.8200\n",
       "Epoch 227/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.3085 - accuracy: 0.8900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3633 - accuracy: 0.8200\n",
       "Epoch 228/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3073 - accuracy: 0.8900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3618 - accuracy: 0.8267\n",
       "Epoch 229/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.3058 - accuracy: 0.8900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3603 - accuracy: 0.8267\n",
       "Epoch 230/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.3044 - accuracy: 0.8900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3590 - accuracy: 0.8267\n",
       "Epoch 231/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3032 - accuracy: 0.8933\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3577 - accuracy: 0.8233\n",
       "Epoch 232/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.3018 - accuracy: 0.8933\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3563 - accuracy: 0.8233\n",
       "Epoch 233/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.3004 - accuracy: 0.8933\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3549 - accuracy: 0.8233\n",
       "Epoch 234/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2991 - accuracy: 0.8933\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3535 - accuracy: 0.8233\n",
       "Epoch 235/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2977 - accuracy: 0.8933\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3522 - accuracy: 0.8267\n",
       "Epoch 236/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.2964 - accuracy: 0.8933\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3509 - accuracy: 0.8267\n",
       "Epoch 237/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.2952 - accuracy: 0.8933\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3498 - accuracy: 0.8267\n",
       "Epoch 238/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.2938 - accuracy: 0.8933\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3484 - accuracy: 0.8300\n",
       "Epoch 239/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.2925 - accuracy: 0.8933\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3468 - accuracy: 0.8333\n",
       "Epoch 240/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.2913 - accuracy: 0.9000\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3458 - accuracy: 0.8300\n",
       "Epoch 241/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.2900 - accuracy: 0.9000\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3443 - accuracy: 0.8300\n",
       "Epoch 242/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.2888 - accuracy: 0.9000\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3429 - accuracy: 0.8333\n",
       "Epoch 243/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.2876 - accuracy: 0.9000\n",
+      "3/3 [==============================] - 0s 17ms/step - loss: 0.3417 - accuracy: 0.8333\n",
       "Epoch 244/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2864 - accuracy: 0.9000\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3403 - accuracy: 0.8367\n",
       "Epoch 245/1000\n",
-      "300/300 [==============================] - 0s 38us/sample - loss: 0.2851 - accuracy: 0.9000\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3391 - accuracy: 0.8333\n",
       "Epoch 246/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.2840 - accuracy: 0.9033\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3379 - accuracy: 0.8367\n",
       "Epoch 247/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.2828 - accuracy: 0.9033\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3366 - accuracy: 0.8400\n",
       "Epoch 248/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.2815 - accuracy: 0.9033\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3353 - accuracy: 0.8400\n",
       "Epoch 249/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.2803 - accuracy: 0.9033\n",
+      "3/3 [==============================] - ETA: 0s - loss: 0.3375 - accuracy: 0.83 - 0s 4ms/step - loss: 0.3341 - accuracy: 0.8433\n",
       "Epoch 250/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.2790 - accuracy: 0.9033\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3328 - accuracy: 0.8433\n",
       "Epoch 251/1000\n",
-      "300/300 [==============================] - 0s 39us/sample - loss: 0.2778 - accuracy: 0.9033\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3316 - accuracy: 0.8433\n",
       "Epoch 252/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.2768 - accuracy: 0.9067\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3304 - accuracy: 0.8433\n",
       "Epoch 253/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.2757 - accuracy: 0.9067\n",
+      "3/3 [==============================] - 0s 21ms/step - loss: 0.3293 - accuracy: 0.8433\n",
       "Epoch 254/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.2745 - accuracy: 0.9033\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3282 - accuracy: 0.8433\n",
       "Epoch 255/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.2734 - accuracy: 0.9033\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3269 - accuracy: 0.8433\n",
       "Epoch 256/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.2721 - accuracy: 0.9033\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3258 - accuracy: 0.8433\n",
       "Epoch 257/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.2710 - accuracy: 0.9033\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3245 - accuracy: 0.8433\n",
       "Epoch 258/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.2700 - accuracy: 0.9067\n",
+      "3/3 [==============================] - 0s 20ms/step - loss: 0.3232 - accuracy: 0.8433\n",
       "Epoch 259/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.2688 - accuracy: 0.9067\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3221 - accuracy: 0.8433\n",
       "Epoch 260/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.2677 - accuracy: 0.9067\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3209 - accuracy: 0.8433\n",
       "Epoch 261/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.2667 - accuracy: 0.9067\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3197 - accuracy: 0.8467\n",
       "Epoch 262/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2656 - accuracy: 0.9067\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3186 - accuracy: 0.8433\n",
       "Epoch 263/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2645 - accuracy: 0.9067\n",
+      "3/3 [==============================] - 0s 18ms/step - loss: 0.3175 - accuracy: 0.8433\n",
       "Epoch 264/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.2635 - accuracy: 0.9067\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3163 - accuracy: 0.8433\n",
       "Epoch 265/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.2624 - accuracy: 0.9067\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3151 - accuracy: 0.8433\n",
       "Epoch 266/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.2613 - accuracy: 0.9067\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3141 - accuracy: 0.8467\n",
       "Epoch 267/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.2603 - accuracy: 0.9067\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3131 - accuracy: 0.8500\n",
       "Epoch 268/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.2592 - accuracy: 0.9067\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3117 - accuracy: 0.8467\n",
       "Epoch 269/1000\n",
-      "300/300 [==============================] - 0s 41us/sample - loss: 0.2581 - accuracy: 0.9100\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3108 - accuracy: 0.8567\n",
       "Epoch 270/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.2572 - accuracy: 0.9100\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.3096 - accuracy: 0.8567\n",
       "Epoch 271/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2562 - accuracy: 0.9100\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3085 - accuracy: 0.8567\n",
       "Epoch 272/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2551 - accuracy: 0.9133\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3074 - accuracy: 0.8567\n",
       "Epoch 273/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.2542 - accuracy: 0.9100\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3064 - accuracy: 0.8600\n",
       "Epoch 274/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.2531 - accuracy: 0.9167\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3052 - accuracy: 0.8600\n",
       "Epoch 275/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.2521 - accuracy: 0.9167\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3041 - accuracy: 0.8600\n",
       "Epoch 276/1000\n",
-      "300/300 [==============================] - 0s 44us/sample - loss: 0.2512 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.3032 - accuracy: 0.8600\n",
       "Epoch 277/1000\n",
-      "300/300 [==============================] - 0s 44us/sample - loss: 0.2502 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3020 - accuracy: 0.8633\n",
       "Epoch 278/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2492 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.3010 - accuracy: 0.8633\n",
       "Epoch 279/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.2482 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2999 - accuracy: 0.8667\n",
       "Epoch 280/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.2473 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2988 - accuracy: 0.8667\n",
       "Epoch 281/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.2463 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2978 - accuracy: 0.8667\n",
       "Epoch 282/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.2454 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2968 - accuracy: 0.8700\n",
       "Epoch 283/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.2445 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2958 - accuracy: 0.8700\n",
       "Epoch 284/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.2435 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2948 - accuracy: 0.8700\n",
       "Epoch 285/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2426 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2938 - accuracy: 0.8700\n",
       "Epoch 286/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.2417 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2927 - accuracy: 0.8700\n",
       "Epoch 287/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2408 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2917 - accuracy: 0.8700\n",
       "Epoch 288/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.2398 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2907 - accuracy: 0.8767\n",
       "Epoch 289/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2389 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2897 - accuracy: 0.8767\n",
       "Epoch 290/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.2380 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2888 - accuracy: 0.8800\n",
       "Epoch 291/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.2372 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2878 - accuracy: 0.8767\n",
       "Epoch 292/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.2362 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.2867 - accuracy: 0.8767\n",
       "Epoch 293/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.2353 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2858 - accuracy: 0.8800\n",
       "Epoch 294/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.2345 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2849 - accuracy: 0.8800\n",
       "Epoch 295/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.2336 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2839 - accuracy: 0.8800\n",
       "Epoch 296/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.2329 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2831 - accuracy: 0.8800\n",
       "Epoch 297/1000\n",
-      "300/300 [==============================] - 0s 24us/sample - loss: 0.2319 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2819 - accuracy: 0.8800\n",
       "Epoch 298/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.2310 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2810 - accuracy: 0.8800\n",
       "Epoch 299/1000\n",
-      "300/300 [==============================] - 0s 41us/sample - loss: 0.2303 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2801 - accuracy: 0.8800\n",
       "Epoch 300/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.2294 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2792 - accuracy: 0.8833\n",
       "Epoch 301/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.2285 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2783 - accuracy: 0.8833\n",
       "Epoch 302/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.2277 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2772 - accuracy: 0.8867\n",
       "Epoch 303/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.2269 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2764 - accuracy: 0.8833\n",
       "Epoch 304/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.2261 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2754 - accuracy: 0.8867\n",
       "Epoch 305/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.2253 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2745 - accuracy: 0.8867\n",
       "Epoch 306/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2244 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2736 - accuracy: 0.8867\n",
       "Epoch 307/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.2237 - accuracy: 0.9200\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2727 - accuracy: 0.8867\n",
       "Epoch 308/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2229 - accuracy: 0.9233\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2719 - accuracy: 0.8867\n",
       "Epoch 309/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.2220 - accuracy: 0.9233\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2709 - accuracy: 0.8867\n",
       "Epoch 310/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.2214 - accuracy: 0.9233\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.2700 - accuracy: 0.8867\n",
       "Epoch 311/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.2206 - accuracy: 0.9233\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2691 - accuracy: 0.8867\n",
       "Epoch 312/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.2197 - accuracy: 0.9233\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2682 - accuracy: 0.8900\n",
       "Epoch 313/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.2190 - accuracy: 0.9233\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2673 - accuracy: 0.8900\n",
       "Epoch 314/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2182 - accuracy: 0.9233\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2665 - accuracy: 0.8900\n",
       "Epoch 315/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.2174 - accuracy: 0.9233\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2656 - accuracy: 0.8933\n",
       "Epoch 316/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.2166 - accuracy: 0.9233\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2648 - accuracy: 0.8933\n",
       "Epoch 317/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.2159 - accuracy: 0.9233\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2640 - accuracy: 0.8933\n",
       "Epoch 318/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.2151 - accuracy: 0.9233\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2631 - accuracy: 0.8967\n",
       "Epoch 319/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.2144 - accuracy: 0.9233\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.2621 - accuracy: 0.8967\n",
       "Epoch 320/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.2138 - accuracy: 0.9300\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2613 - accuracy: 0.8967\n",
       "Epoch 321/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.2129 - accuracy: 0.9300\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2605 - accuracy: 0.8967\n",
       "Epoch 322/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2122 - accuracy: 0.9300\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2598 - accuracy: 0.8933\n",
       "Epoch 323/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2115 - accuracy: 0.9300\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2588 - accuracy: 0.8967\n",
       "Epoch 324/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2107 - accuracy: 0.9300\n",
+      "3/3 [==============================] - 0s 7ms/step - loss: 0.2580 - accuracy: 0.8967\n",
       "Epoch 325/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.2100 - accuracy: 0.9300\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2571 - accuracy: 0.8967\n",
       "Epoch 326/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.2093 - accuracy: 0.9300\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2563 - accuracy: 0.8933\n",
       "Epoch 327/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.2086 - accuracy: 0.9300\n",
+      "3/3 [==============================] - 0s 7ms/step - loss: 0.2555 - accuracy: 0.8967\n",
       "Epoch 328/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.2080 - accuracy: 0.9300\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2547 - accuracy: 0.9000\n",
       "Epoch 329/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.2072 - accuracy: 0.9333\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2540 - accuracy: 0.9000\n",
       "Epoch 330/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.2065 - accuracy: 0.9333\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2531 - accuracy: 0.9000\n",
       "Epoch 331/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2058 - accuracy: 0.9333\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2524 - accuracy: 0.8967\n",
       "Epoch 332/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.2052 - accuracy: 0.9367\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2515 - accuracy: 0.8967\n",
       "Epoch 333/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.2044 - accuracy: 0.9333\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2507 - accuracy: 0.8967\n",
       "Epoch 334/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.2037 - accuracy: 0.9333\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2498 - accuracy: 0.9000\n",
       "Epoch 335/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.2031 - accuracy: 0.9333\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2492 - accuracy: 0.9000\n",
       "Epoch 336/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.2024 - accuracy: 0.9367\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2485 - accuracy: 0.9000\n",
       "Epoch 337/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.2017 - accuracy: 0.9367\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2476 - accuracy: 0.9000\n",
       "Epoch 338/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.2010 - accuracy: 0.9333\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2468 - accuracy: 0.9000\n",
       "Epoch 339/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.2005 - accuracy: 0.9367\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.2461 - accuracy: 0.9000\n",
       "Epoch 340/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.1997 - accuracy: 0.9367\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2453 - accuracy: 0.9000\n",
       "Epoch 341/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1992 - accuracy: 0.9333\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2445 - accuracy: 0.9000\n",
       "Epoch 342/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1985 - accuracy: 0.9367\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2438 - accuracy: 0.9033\n",
       "Epoch 343/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1979 - accuracy: 0.9400\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2430 - accuracy: 0.9033\n",
       "Epoch 344/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1971 - accuracy: 0.9367\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2422 - accuracy: 0.9000\n",
       "Epoch 345/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1965 - accuracy: 0.9367\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2415 - accuracy: 0.9000\n",
       "Epoch 346/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1959 - accuracy: 0.9367\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2409 - accuracy: 0.9000\n",
       "Epoch 347/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1953 - accuracy: 0.9367\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2401 - accuracy: 0.9033\n",
       "Epoch 348/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1946 - accuracy: 0.9367\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2392 - accuracy: 0.9033\n",
       "Epoch 349/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1940 - accuracy: 0.9400\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2386 - accuracy: 0.9033\n",
       "Epoch 350/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1933 - accuracy: 0.9400\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2379 - accuracy: 0.9067\n",
       "Epoch 351/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1927 - accuracy: 0.9400\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2373 - accuracy: 0.9033\n",
       "Epoch 352/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1921 - accuracy: 0.9400\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.2364 - accuracy: 0.9033\n",
       "Epoch 353/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.1915 - accuracy: 0.9400\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2357 - accuracy: 0.9033\n",
       "Epoch 354/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.1909 - accuracy: 0.9400\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.2349 - accuracy: 0.9067\n",
       "Epoch 355/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1903 - accuracy: 0.9433\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2343 - accuracy: 0.9067\n",
       "Epoch 356/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1897 - accuracy: 0.9433\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2336 - accuracy: 0.9067\n",
       "Epoch 357/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1891 - accuracy: 0.9433\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2328 - accuracy: 0.9067\n",
       "Epoch 358/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.1885 - accuracy: 0.9433\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2321 - accuracy: 0.9133\n",
       "Epoch 359/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1879 - accuracy: 0.9400\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2315 - accuracy: 0.9133\n",
       "Epoch 360/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1874 - accuracy: 0.9433\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2309 - accuracy: 0.9133\n",
       "Epoch 361/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1868 - accuracy: 0.9433\n",
+      "3/3 [==============================] - ETA: 0s - loss: 0.1736 - accuracy: 0.95 - 0s 4ms/step - loss: 0.2300 - accuracy: 0.9133\n",
       "Epoch 362/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1861 - accuracy: 0.9433\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2295 - accuracy: 0.9100\n",
       "Epoch 363/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1856 - accuracy: 0.9433\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2288 - accuracy: 0.9100\n",
       "Epoch 364/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.1850 - accuracy: 0.9433\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2281 - accuracy: 0.9067\n",
       "Epoch 365/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.1844 - accuracy: 0.9433\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2273 - accuracy: 0.9100\n",
       "Epoch 366/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1838 - accuracy: 0.9433\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2268 - accuracy: 0.9133\n",
       "Epoch 367/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.1834 - accuracy: 0.9433\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2261 - accuracy: 0.9133\n",
       "Epoch 368/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1828 - accuracy: 0.9433\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2255 - accuracy: 0.9133\n",
       "Epoch 369/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1822 - accuracy: 0.9433\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2247 - accuracy: 0.9167\n",
       "Epoch 370/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1817 - accuracy: 0.9433\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2241 - accuracy: 0.9167\n",
       "Epoch 371/1000\n",
-      "300/300 [==============================] - 0s 38us/sample - loss: 0.1811 - accuracy: 0.9467\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2235 - accuracy: 0.9167\n",
       "Epoch 372/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1806 - accuracy: 0.9467\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2228 - accuracy: 0.9167\n",
       "Epoch 373/1000\n",
-      "300/300 [==============================] - 0s 25us/sample - loss: 0.1799 - accuracy: 0.9467\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2222 - accuracy: 0.9167\n",
       "Epoch 374/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1794 - accuracy: 0.9467\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2215 - accuracy: 0.9200\n",
       "Epoch 375/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1789 - accuracy: 0.9467\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2208 - accuracy: 0.9200\n",
       "Epoch 376/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.1783 - accuracy: 0.9467\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2202 - accuracy: 0.9200\n",
       "Epoch 377/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.1778 - accuracy: 0.9467\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2196 - accuracy: 0.9200\n",
       "Epoch 378/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.1773 - accuracy: 0.9467\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2190 - accuracy: 0.9200\n",
       "Epoch 379/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1767 - accuracy: 0.9467\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2182 - accuracy: 0.9200\n",
       "Epoch 380/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.1762 - accuracy: 0.9467\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2178 - accuracy: 0.9233\n",
       "Epoch 381/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.1757 - accuracy: 0.9467\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2171 - accuracy: 0.9233\n",
       "Epoch 382/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1751 - accuracy: 0.9467\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2164 - accuracy: 0.9233\n",
       "Epoch 383/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1746 - accuracy: 0.9467\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2159 - accuracy: 0.9233\n",
       "Epoch 384/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.1742 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2152 - accuracy: 0.9267\n",
       "Epoch 385/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.1736 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2147 - accuracy: 0.9267\n",
       "Epoch 386/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1732 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2140 - accuracy: 0.9267\n",
       "Epoch 387/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1727 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2133 - accuracy: 0.9267\n",
       "Epoch 388/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1722 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2127 - accuracy: 0.9267\n",
       "Epoch 389/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1716 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2122 - accuracy: 0.9233\n",
       "Epoch 390/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1711 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2115 - accuracy: 0.9300\n",
       "Epoch 391/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1707 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2110 - accuracy: 0.9267\n",
       "Epoch 392/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1701 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2104 - accuracy: 0.9267\n",
       "Epoch 393/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1696 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2098 - accuracy: 0.9300\n",
       "Epoch 394/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1692 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.2091 - accuracy: 0.9300\n",
       "Epoch 395/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1686 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2086 - accuracy: 0.9267\n",
       "Epoch 396/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1683 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2080 - accuracy: 0.9267\n",
       "Epoch 397/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.1676 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2076 - accuracy: 0.9267\n",
       "Epoch 398/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.1671 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2070 - accuracy: 0.9300\n",
       "Epoch 399/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1667 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2064 - accuracy: 0.9267\n",
       "Epoch 400/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1662 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2057 - accuracy: 0.9267\n",
       "Epoch 401/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.1657 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2051 - accuracy: 0.9267\n",
       "Epoch 402/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1652 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2046 - accuracy: 0.9267\n",
       "Epoch 403/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1649 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2040 - accuracy: 0.9333\n",
       "Epoch 404/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.1644 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2034 - accuracy: 0.9333\n",
       "Epoch 405/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1638 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2029 - accuracy: 0.9300\n",
       "Epoch 406/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.1634 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2023 - accuracy: 0.9333\n",
       "Epoch 407/1000\n",
-      "300/300 [==============================] - 0s 39us/sample - loss: 0.1629 - accuracy: 0.9533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2017 - accuracy: 0.9333\n",
       "Epoch 408/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.1624 - accuracy: 0.9533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2013 - accuracy: 0.9333\n",
       "Epoch 409/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1620 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2007 - accuracy: 0.9367\n",
       "Epoch 410/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1615 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.2001 - accuracy: 0.9333\n",
       "Epoch 411/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1611 - accuracy: 0.9500\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1995 - accuracy: 0.9367\n",
       "Epoch 412/1000\n",
-      "300/300 [==============================] - 0s 24us/sample - loss: 0.1607 - accuracy: 0.9533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1990 - accuracy: 0.9400\n",
       "Epoch 413/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1602 - accuracy: 0.9533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1984 - accuracy: 0.9367\n",
       "Epoch 414/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.1598 - accuracy: 0.9533\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1980 - accuracy: 0.9367\n",
       "Epoch 415/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1593 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1975 - accuracy: 0.9400\n",
       "Epoch 416/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.1588 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1968 - accuracy: 0.9400\n",
       "Epoch 417/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1584 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1963 - accuracy: 0.9400\n",
       "Epoch 418/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1580 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.1957 - accuracy: 0.9367\n",
       "Epoch 419/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1576 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1953 - accuracy: 0.9367\n",
       "Epoch 420/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1571 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1948 - accuracy: 0.9367\n",
       "Epoch 421/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.1568 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1942 - accuracy: 0.9400\n",
       "Epoch 422/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1563 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1937 - accuracy: 0.9400\n",
       "Epoch 423/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1559 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1932 - accuracy: 0.9400\n",
       "Epoch 424/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1555 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1927 - accuracy: 0.9433\n",
       "Epoch 425/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1550 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1922 - accuracy: 0.9433\n",
       "Epoch 426/1000\n",
-      "300/300 [==============================] - 0s 42us/sample - loss: 0.1546 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1916 - accuracy: 0.9433\n",
       "Epoch 427/1000\n",
-      "300/300 [==============================] - 0s 53us/sample - loss: 0.1542 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1911 - accuracy: 0.9433\n",
       "Epoch 428/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1538 - accuracy: 0.9533\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1907 - accuracy: 0.9400\n",
       "Epoch 429/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1534 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1900 - accuracy: 0.9400\n",
       "Epoch 430/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1529 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1896 - accuracy: 0.9400\n",
       "Epoch 431/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.1525 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1891 - accuracy: 0.9433\n",
       "Epoch 432/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1521 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1886 - accuracy: 0.9433\n",
       "Epoch 433/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.1517 - accuracy: 0.9567\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.1881 - accuracy: 0.9433\n",
       "Epoch 434/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1513 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 6ms/step - loss: 0.1875 - accuracy: 0.9433\n",
       "Epoch 435/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.1509 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1871 - accuracy: 0.9433\n",
       "Epoch 436/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1505 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1866 - accuracy: 0.9433\n",
       "Epoch 437/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1501 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1860 - accuracy: 0.9433\n",
       "Epoch 438/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1496 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1856 - accuracy: 0.9433\n",
       "Epoch 439/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1493 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1851 - accuracy: 0.9433\n",
       "Epoch 440/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1489 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1846 - accuracy: 0.9433\n",
       "Epoch 441/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1486 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1841 - accuracy: 0.9433\n",
       "Epoch 442/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1482 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1838 - accuracy: 0.9433\n",
       "Epoch 443/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1479 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1832 - accuracy: 0.9433\n",
       "Epoch 444/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1475 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1828 - accuracy: 0.9433\n",
       "Epoch 445/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1470 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1822 - accuracy: 0.9433\n",
       "Epoch 446/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1466 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1818 - accuracy: 0.9433\n",
       "Epoch 447/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1462 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1812 - accuracy: 0.9433\n",
       "Epoch 448/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1458 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.1809 - accuracy: 0.9433\n",
       "Epoch 449/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1455 - accuracy: 0.9633\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1804 - accuracy: 0.9433\n",
       "Epoch 450/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1451 - accuracy: 0.9633\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1799 - accuracy: 0.9433\n",
       "Epoch 451/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1447 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1794 - accuracy: 0.9433\n",
       "Epoch 452/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1443 - accuracy: 0.9600\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1789 - accuracy: 0.9433\n",
       "Epoch 453/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1439 - accuracy: 0.9633\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1786 - accuracy: 0.9433\n",
       "Epoch 454/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1436 - accuracy: 0.9633\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1781 - accuracy: 0.9433\n",
       "Epoch 455/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1432 - accuracy: 0.9633\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1775 - accuracy: 0.9433\n",
       "Epoch 456/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1429 - accuracy: 0.9633\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1771 - accuracy: 0.9433\n",
       "Epoch 457/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1425 - accuracy: 0.9633\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1767 - accuracy: 0.9433\n",
       "Epoch 458/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1421 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1763 - accuracy: 0.9433\n",
       "Epoch 459/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1418 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1758 - accuracy: 0.9433\n",
       "Epoch 460/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1414 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1753 - accuracy: 0.9467\n",
       "Epoch 461/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1411 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1748 - accuracy: 0.9467\n",
       "Epoch 462/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1407 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1744 - accuracy: 0.9467\n",
       "Epoch 463/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1403 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1741 - accuracy: 0.9500\n",
       "Epoch 464/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1400 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1736 - accuracy: 0.9467\n",
       "Epoch 465/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1396 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1732 - accuracy: 0.9467\n",
       "Epoch 466/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1393 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1727 - accuracy: 0.9467\n",
       "Epoch 467/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1389 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1722 - accuracy: 0.9467\n",
       "Epoch 468/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1386 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1719 - accuracy: 0.9467\n",
       "Epoch 469/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.1383 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1715 - accuracy: 0.9467\n",
       "Epoch 470/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.1380 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1710 - accuracy: 0.9467\n",
       "Epoch 471/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1376 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.1706 - accuracy: 0.9500\n",
       "Epoch 472/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1373 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1701 - accuracy: 0.9467\n",
       "Epoch 473/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1369 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1697 - accuracy: 0.9500\n",
       "Epoch 474/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.1366 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1692 - accuracy: 0.9467\n",
       "Epoch 475/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1364 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1688 - accuracy: 0.9500\n",
       "Epoch 476/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1360 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1683 - accuracy: 0.9533\n",
       "Epoch 477/1000\n",
-      "300/300 [==============================] - 0s 24us/sample - loss: 0.1355 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1680 - accuracy: 0.9533\n",
       "Epoch 478/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1352 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1675 - accuracy: 0.9533\n",
       "Epoch 479/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1349 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1672 - accuracy: 0.9533\n",
       "Epoch 480/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1346 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1667 - accuracy: 0.9533\n",
       "Epoch 481/1000\n",
-      "300/300 [==============================] - 0s 44us/sample - loss: 0.1343 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1663 - accuracy: 0.9533\n",
       "Epoch 482/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.1340 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1659 - accuracy: 0.9500\n",
       "Epoch 483/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.1337 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1656 - accuracy: 0.9533\n",
       "Epoch 484/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1334 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 12ms/step - loss: 0.1652 - accuracy: 0.9533\n",
       "Epoch 485/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1330 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1646 - accuracy: 0.9533\n",
       "Epoch 486/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.1327 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1642 - accuracy: 0.9567\n",
       "Epoch 487/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.1324 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1639 - accuracy: 0.9533\n",
       "Epoch 488/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.1321 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1634 - accuracy: 0.9533\n",
       "Epoch 489/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.1317 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1630 - accuracy: 0.9533\n",
       "Epoch 490/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.1314 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1627 - accuracy: 0.9533\n",
       "Epoch 491/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.1311 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1622 - accuracy: 0.9533\n",
       "Epoch 492/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1308 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1618 - accuracy: 0.9533\n",
       "Epoch 493/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1304 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1616 - accuracy: 0.9533\n",
       "Epoch 494/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1302 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1610 - accuracy: 0.9567\n",
       "Epoch 495/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1299 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1607 - accuracy: 0.9533\n",
       "Epoch 496/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.1296 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1603 - accuracy: 0.9533\n",
       "Epoch 497/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1293 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1598 - accuracy: 0.9567\n",
       "Epoch 498/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.1290 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1595 - accuracy: 0.9567\n",
       "Epoch 499/1000\n",
-      "300/300 [==============================] - ETA: 0s - loss: 0.1275 - accuracy: 0.96 - 0s 28us/sample - loss: 0.1289 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1592 - accuracy: 0.9567\n",
       "Epoch 500/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1284 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 22ms/step - loss: 0.1587 - accuracy: 0.9567\n",
       "Epoch 501/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1280 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1583 - accuracy: 0.9567\n",
       "Epoch 502/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1277 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1580 - accuracy: 0.9533\n",
       "Epoch 503/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1275 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1575 - accuracy: 0.9533\n",
       "Epoch 504/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1271 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 21ms/step - loss: 0.1573 - accuracy: 0.9533\n",
       "Epoch 505/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1268 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1568 - accuracy: 0.9533\n",
       "Epoch 506/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1265 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1564 - accuracy: 0.9567\n",
       "Epoch 507/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1263 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1561 - accuracy: 0.9500\n",
       "Epoch 508/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1260 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1556 - accuracy: 0.9567\n",
       "Epoch 509/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1257 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1553 - accuracy: 0.9567\n",
       "Epoch 510/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.1255 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 11ms/step - loss: 0.1549 - accuracy: 0.9567\n",
       "Epoch 511/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.1251 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1545 - accuracy: 0.9567\n",
       "Epoch 512/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.1248 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1541 - accuracy: 0.9567\n",
       "Epoch 513/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1245 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1539 - accuracy: 0.9567\n",
       "Epoch 514/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.1242 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1534 - accuracy: 0.9567\n",
       "Epoch 515/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1239 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1530 - accuracy: 0.9567\n",
       "Epoch 516/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1237 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1527 - accuracy: 0.9567\n",
       "Epoch 517/1000\n",
-      "300/300 [==============================] - 0s 51us/sample - loss: 0.1234 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1523 - accuracy: 0.9567\n",
       "Epoch 518/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1232 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1519 - accuracy: 0.9567\n",
       "Epoch 519/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1228 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1516 - accuracy: 0.9567\n",
       "Epoch 520/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1226 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1513 - accuracy: 0.9567\n",
       "Epoch 521/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1223 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1509 - accuracy: 0.9567\n",
       "Epoch 522/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1220 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1506 - accuracy: 0.9567\n",
       "Epoch 523/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1217 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1503 - accuracy: 0.9567\n",
       "Epoch 524/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1215 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1499 - accuracy: 0.9567\n",
       "Epoch 525/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.1212 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1496 - accuracy: 0.9533\n",
       "Epoch 526/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1209 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1491 - accuracy: 0.9567\n",
       "Epoch 527/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1206 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1488 - accuracy: 0.9567\n",
       "Epoch 528/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1204 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1484 - accuracy: 0.9567\n",
       "Epoch 529/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1201 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1480 - accuracy: 0.9633\n",
       "Epoch 530/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1199 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1477 - accuracy: 0.9600\n",
       "Epoch 531/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1195 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1474 - accuracy: 0.9600\n",
       "Epoch 532/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1193 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1470 - accuracy: 0.9633\n",
       "Epoch 533/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1190 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 6ms/step - loss: 0.1467 - accuracy: 0.9633\n",
       "Epoch 534/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1189 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1463 - accuracy: 0.9633\n",
       "Epoch 535/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1186 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1460 - accuracy: 0.9633\n",
       "Epoch 536/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.1183 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1457 - accuracy: 0.9567\n",
       "Epoch 537/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1180 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1453 - accuracy: 0.9600\n",
       "Epoch 538/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1178 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1449 - accuracy: 0.9633\n",
       "Epoch 539/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1175 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 6ms/step - loss: 0.1446 - accuracy: 0.9633\n",
       "Epoch 540/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1172 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 6ms/step - loss: 0.1444 - accuracy: 0.9633\n",
       "Epoch 541/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1170 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1440 - accuracy: 0.9633\n",
       "Epoch 542/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1168 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1436 - accuracy: 0.9633\n",
       "Epoch 543/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1165 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1434 - accuracy: 0.9633\n",
       "Epoch 544/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1162 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.1430 - accuracy: 0.9633\n",
       "Epoch 545/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1160 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 7ms/step - loss: 0.1426 - accuracy: 0.9600\n",
       "Epoch 546/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1157 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1424 - accuracy: 0.9600\n",
       "Epoch 547/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1155 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1420 - accuracy: 0.9633\n",
       "Epoch 548/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1153 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1417 - accuracy: 0.9633\n",
       "Epoch 549/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1150 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1414 - accuracy: 0.9633\n",
       "Epoch 550/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1148 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1411 - accuracy: 0.9633\n",
       "Epoch 551/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1145 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1408 - accuracy: 0.9600\n",
       "Epoch 552/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1143 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 11ms/step - loss: 0.1404 - accuracy: 0.9633\n",
       "Epoch 553/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1140 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1401 - accuracy: 0.9633\n",
       "Epoch 554/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1137 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1398 - accuracy: 0.9600\n",
       "Epoch 555/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.1135 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1395 - accuracy: 0.9633\n",
       "Epoch 556/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.1133 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1392 - accuracy: 0.9633\n",
       "Epoch 557/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.1131 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1390 - accuracy: 0.9633\n",
       "Epoch 558/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1128 - accuracy: 0.9667\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1385 - accuracy: 0.9633\n",
       "Epoch 559/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.1127 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1382 - accuracy: 0.9633\n",
       "Epoch 560/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.1124 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1379 - accuracy: 0.9633\n",
       "Epoch 561/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1121 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1377 - accuracy: 0.9633\n",
       "Epoch 562/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1119 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1374 - accuracy: 0.9667\n",
       "Epoch 563/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1116 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1370 - accuracy: 0.9667\n",
       "Epoch 564/1000\n",
-      "300/300 [==============================] - 0s 44us/sample - loss: 0.1115 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1367 - accuracy: 0.9667\n",
       "Epoch 565/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1112 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1365 - accuracy: 0.9667\n",
       "Epoch 566/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.1110 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1361 - accuracy: 0.9700\n",
       "Epoch 567/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.1109 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1358 - accuracy: 0.9700\n",
       "Epoch 568/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1106 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1356 - accuracy: 0.9633\n",
       "Epoch 569/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1103 - accuracy: 0.9700\n",
+      "3/3 [==============================] - ETA: 0s - loss: 0.1524 - accuracy: 0.95 - 0s 3ms/step - loss: 0.1353 - accuracy: 0.9667\n",
       "Epoch 570/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.1100 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.1349 - accuracy: 0.9667\n",
       "Epoch 571/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1099 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1346 - accuracy: 0.9700\n",
       "Epoch 572/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1097 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1343 - accuracy: 0.9700\n",
       "Epoch 573/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1094 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1340 - accuracy: 0.9700\n",
       "Epoch 574/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.1092 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1337 - accuracy: 0.9667\n",
       "Epoch 575/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.1089 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1335 - accuracy: 0.9633\n",
       "Epoch 576/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1087 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1332 - accuracy: 0.9667\n",
       "Epoch 577/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1085 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1329 - accuracy: 0.9700\n",
       "Epoch 578/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1083 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1325 - accuracy: 0.9700\n",
       "Epoch 579/1000\n",
-      "300/300 [==============================] - 0s 25us/sample - loss: 0.1080 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1322 - accuracy: 0.9700\n",
       "Epoch 580/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1078 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1322 - accuracy: 0.9700\n",
       "Epoch 581/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1077 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1317 - accuracy: 0.9700\n",
       "Epoch 582/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1074 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1315 - accuracy: 0.9700\n",
       "Epoch 583/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1072 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1312 - accuracy: 0.9667\n",
       "Epoch 584/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1070 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1309 - accuracy: 0.9667\n",
       "Epoch 585/1000\n",
-      "300/300 [==============================] - 0s 39us/sample - loss: 0.1067 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1306 - accuracy: 0.9667\n",
       "Epoch 586/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.1065 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1304 - accuracy: 0.9667\n",
       "Epoch 587/1000\n",
-      "300/300 [==============================] - 0s 40us/sample - loss: 0.1063 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1300 - accuracy: 0.9667\n",
       "Epoch 588/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.1061 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1297 - accuracy: 0.9667\n",
       "Epoch 589/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.1059 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1294 - accuracy: 0.9700\n",
       "Epoch 590/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1057 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1293 - accuracy: 0.9633\n",
       "Epoch 591/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.1055 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1289 - accuracy: 0.9667\n",
       "Epoch 592/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1052 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1286 - accuracy: 0.9700\n",
       "Epoch 593/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1050 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1284 - accuracy: 0.9700\n",
       "Epoch 594/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1049 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1281 - accuracy: 0.9700\n",
       "Epoch 595/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1046 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1278 - accuracy: 0.9700\n",
       "Epoch 596/1000\n",
-      "300/300 [==============================] - ETA: 0s - loss: 0.0744 - accuracy: 0.97 - 0s 28us/sample - loss: 0.1045 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.1275 - accuracy: 0.9700\n",
       "Epoch 597/1000\n",
-      "300/300 [==============================] - 0s 39us/sample - loss: 0.1042 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1273 - accuracy: 0.9700\n",
       "Epoch 598/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.1040 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1270 - accuracy: 0.9700\n",
       "Epoch 599/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.1038 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1268 - accuracy: 0.9700\n",
       "Epoch 600/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.1035 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1266 - accuracy: 0.9700\n",
       "Epoch 601/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1034 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1262 - accuracy: 0.9733\n",
       "Epoch 602/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.1032 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1260 - accuracy: 0.9733\n",
       "Epoch 603/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1030 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1257 - accuracy: 0.9733\n",
       "Epoch 604/1000\n",
-      "300/300 [==============================] - 0s 39us/sample - loss: 0.1028 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1254 - accuracy: 0.9733\n",
       "Epoch 605/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1026 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1252 - accuracy: 0.9733\n",
       "Epoch 606/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.1024 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1249 - accuracy: 0.9733\n",
       "Epoch 607/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1022 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1246 - accuracy: 0.9800\n",
       "Epoch 608/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1020 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1244 - accuracy: 0.9767\n",
       "Epoch 609/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.1019 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1241 - accuracy: 0.9800\n",
       "Epoch 610/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1016 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1238 - accuracy: 0.9800\n",
       "Epoch 611/1000\n",
-      "300/300 [==============================] - ETA: 0s - loss: 0.0970 - accuracy: 0.97 - 0s 30us/sample - loss: 0.1014 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1236 - accuracy: 0.9733\n",
       "Epoch 612/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.1012 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.1233 - accuracy: 0.9733\n",
       "Epoch 613/1000\n",
-      "300/300 [==============================] - ETA: 0s - loss: 0.1110 - accuracy: 0.97 - 0s 28us/sample - loss: 0.1010 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1231 - accuracy: 0.9700\n",
       "Epoch 614/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1009 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1229 - accuracy: 0.9733\n",
       "Epoch 615/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1007 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1226 - accuracy: 0.9767\n",
       "Epoch 616/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.1004 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1224 - accuracy: 0.9733\n",
       "Epoch 617/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.1002 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1221 - accuracy: 0.9767\n",
       "Epoch 618/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.1000 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1218 - accuracy: 0.9767\n",
       "Epoch 619/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0998 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1216 - accuracy: 0.9800\n",
       "Epoch 620/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0996 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1213 - accuracy: 0.9767\n",
       "Epoch 621/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0995 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1211 - accuracy: 0.9767\n",
       "Epoch 622/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0993 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 6ms/step - loss: 0.1208 - accuracy: 0.9767\n",
       "Epoch 623/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0991 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1205 - accuracy: 0.9767\n",
       "Epoch 624/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0989 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1202 - accuracy: 0.9767\n",
       "Epoch 625/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0987 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1201 - accuracy: 0.9767\n",
       "Epoch 626/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0986 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1199 - accuracy: 0.9767\n",
       "Epoch 627/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0983 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1195 - accuracy: 0.9767\n",
       "Epoch 628/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0981 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1195 - accuracy: 0.9767\n",
       "Epoch 629/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0979 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1191 - accuracy: 0.9800\n",
       "Epoch 630/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0978 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1188 - accuracy: 0.9800\n",
       "Epoch 631/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0976 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1186 - accuracy: 0.9800\n",
       "Epoch 632/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0974 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1185 - accuracy: 0.9800\n",
       "Epoch 633/1000\n",
-      "300/300 [==============================] - 0s 39us/sample - loss: 0.0972 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1181 - accuracy: 0.9833\n",
       "Epoch 634/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0971 - accuracy: 0.9700\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1179 - accuracy: 0.9800\n",
       "Epoch 635/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0969 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1176 - accuracy: 0.9800\n",
       "Epoch 636/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0967 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1174 - accuracy: 0.9800\n",
       "Epoch 637/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0965 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1171 - accuracy: 0.9800\n",
       "Epoch 638/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0964 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1169 - accuracy: 0.9800\n",
       "Epoch 639/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0962 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1168 - accuracy: 0.9800\n",
       "Epoch 640/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0960 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1165 - accuracy: 0.9800\n",
       "Epoch 641/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0958 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1162 - accuracy: 0.9800\n",
       "Epoch 642/1000\n",
-      "300/300 [==============================] - 0s 25us/sample - loss: 0.0956 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1160 - accuracy: 0.9800\n",
       "Epoch 643/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0955 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 7ms/step - loss: 0.1158 - accuracy: 0.9800\n",
       "Epoch 644/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0953 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1154 - accuracy: 0.9800\n",
       "Epoch 645/1000\n",
-      "300/300 [==============================] - 0s 25us/sample - loss: 0.0951 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1153 - accuracy: 0.9833\n",
       "Epoch 646/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0950 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1150 - accuracy: 0.9833\n",
       "Epoch 647/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0948 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1147 - accuracy: 0.9833\n",
       "Epoch 648/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0946 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1145 - accuracy: 0.9833\n",
       "Epoch 649/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0944 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1143 - accuracy: 0.9833\n",
       "Epoch 650/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0942 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1141 - accuracy: 0.9800\n",
       "Epoch 651/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0940 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1139 - accuracy: 0.9767\n",
       "Epoch 652/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0940 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1137 - accuracy: 0.9833\n",
       "Epoch 653/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.0937 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1134 - accuracy: 0.9833\n",
       "Epoch 654/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0935 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1132 - accuracy: 0.9800\n",
       "Epoch 655/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0934 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1129 - accuracy: 0.9800\n",
       "Epoch 656/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0932 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1127 - accuracy: 0.9800\n",
       "Epoch 657/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0932 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1125 - accuracy: 0.9800\n",
       "Epoch 658/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0929 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1122 - accuracy: 0.9800\n",
       "Epoch 659/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0928 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1120 - accuracy: 0.9800\n",
       "Epoch 660/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0925 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1118 - accuracy: 0.9800\n",
       "Epoch 661/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0924 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1116 - accuracy: 0.9800\n",
       "Epoch 662/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0922 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1114 - accuracy: 0.9800\n",
       "Epoch 663/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0921 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1111 - accuracy: 0.9800\n",
       "Epoch 664/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0919 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1109 - accuracy: 0.9833\n",
       "Epoch 665/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0918 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1106 - accuracy: 0.9833\n",
       "Epoch 666/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0916 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1105 - accuracy: 0.9800\n",
       "Epoch 667/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0914 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1102 - accuracy: 0.9800\n",
       "Epoch 668/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0912 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1100 - accuracy: 0.9800\n",
       "Epoch 669/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0911 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1099 - accuracy: 0.9800\n",
       "Epoch 670/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.0909 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1096 - accuracy: 0.9800\n",
       "Epoch 671/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0907 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1095 - accuracy: 0.9800\n",
       "Epoch 672/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0906 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1091 - accuracy: 0.9800\n",
       "Epoch 673/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.0904 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1090 - accuracy: 0.9833\n",
       "Epoch 674/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0903 - accuracy: 0.9733\n",
+      "3/3 [==============================] - ETA: 0s - loss: 0.1040 - accuracy: 1.00 - 0s 3ms/step - loss: 0.1088 - accuracy: 0.9833\n",
       "Epoch 675/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0901 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 8ms/step - loss: 0.1085 - accuracy: 0.9833\n",
       "Epoch 676/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0899 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1083 - accuracy: 0.9833\n",
       "Epoch 677/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0898 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1080 - accuracy: 0.9833\n",
       "Epoch 678/1000\n",
-      "300/300 [==============================] - ETA: 0s - loss: 0.0878 - accuracy: 0.96 - 0s 30us/sample - loss: 0.0897 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1079 - accuracy: 0.9800\n",
       "Epoch 679/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0895 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1077 - accuracy: 0.9800\n",
       "Epoch 680/1000\n",
-      "300/300 [==============================] - 0s 38us/sample - loss: 0.0893 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1074 - accuracy: 0.9800\n",
       "Epoch 681/1000\n",
-      "300/300 [==============================] - ETA: 0s - loss: 0.0852 - accuracy: 0.97 - 0s 31us/sample - loss: 0.0892 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1073 - accuracy: 0.9833\n",
       "Epoch 682/1000\n",
-      "300/300 [==============================] - 0s 39us/sample - loss: 0.0890 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1071 - accuracy: 0.9800\n",
       "Epoch 683/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0888 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1069 - accuracy: 0.9800\n",
       "Epoch 684/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0887 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1066 - accuracy: 0.9800\n",
       "Epoch 685/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0885 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1064 - accuracy: 0.9800\n",
       "Epoch 686/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0884 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.1062 - accuracy: 0.9833\n",
       "Epoch 687/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0882 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1059 - accuracy: 0.9833\n",
       "Epoch 688/1000\n",
-      "300/300 [==============================] - 0s 41us/sample - loss: 0.0881 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1058 - accuracy: 0.9833\n",
       "Epoch 689/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.0879 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1056 - accuracy: 0.9833\n",
       "Epoch 690/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.0878 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1054 - accuracy: 0.9833\n",
       "Epoch 691/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0876 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1053 - accuracy: 0.9833\n",
       "Epoch 692/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0875 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.1050 - accuracy: 0.9800\n",
       "Epoch 693/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0873 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.1048 - accuracy: 0.9800\n",
       "Epoch 694/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0872 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1046 - accuracy: 0.9833\n",
       "Epoch 695/1000\n",
-      "300/300 [==============================] - 0s 43us/sample - loss: 0.0870 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1043 - accuracy: 0.9833\n",
       "Epoch 696/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0869 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1042 - accuracy: 0.9833\n",
       "Epoch 697/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0867 - accuracy: 0.9733\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1040 - accuracy: 0.9833\n",
       "Epoch 698/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0866 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1038 - accuracy: 0.9800\n",
       "Epoch 699/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0864 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1036 - accuracy: 0.9833\n",
       "Epoch 700/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0863 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1034 - accuracy: 0.9800\n",
       "Epoch 701/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0861 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1032 - accuracy: 0.9800\n",
       "Epoch 702/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0860 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1029 - accuracy: 0.9833\n",
       "Epoch 703/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0858 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1028 - accuracy: 0.9833\n",
       "Epoch 704/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0857 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1026 - accuracy: 0.9833\n",
       "Epoch 705/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0855 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1026 - accuracy: 0.9833\n",
       "Epoch 706/1000\n",
-      "300/300 [==============================] - 0s 24us/sample - loss: 0.0854 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1022 - accuracy: 0.9833\n",
       "Epoch 707/1000\n",
-      "300/300 [==============================] - 0s 25us/sample - loss: 0.0853 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1020 - accuracy: 0.9800\n",
       "Epoch 708/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0851 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1019 - accuracy: 0.9833\n",
       "Epoch 709/1000\n",
-      "300/300 [==============================] - 0s 39us/sample - loss: 0.0850 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1016 - accuracy: 0.9833\n",
       "Epoch 710/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0848 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1015 - accuracy: 0.9800\n",
       "Epoch 711/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0847 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1013 - accuracy: 0.9800\n",
       "Epoch 712/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0846 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1011 - accuracy: 0.9800\n",
       "Epoch 713/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0844 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.1010 - accuracy: 0.9800\n",
       "Epoch 714/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0843 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1007 - accuracy: 0.9800\n",
       "Epoch 715/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0841 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1005 - accuracy: 0.9800\n",
       "Epoch 716/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0840 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.1004 - accuracy: 0.9833\n",
       "Epoch 717/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.0839 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.1002 - accuracy: 0.9833\n",
       "Epoch 718/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0838 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0999 - accuracy: 0.9833\n",
       "Epoch 719/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0835 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0998 - accuracy: 0.9800\n",
       "Epoch 720/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0835 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0997 - accuracy: 0.9833\n",
       "Epoch 721/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0834 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 9ms/step - loss: 0.0994 - accuracy: 0.9833\n",
       "Epoch 722/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0831 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0993 - accuracy: 0.9833\n",
       "Epoch 723/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0830 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0990 - accuracy: 0.9833\n",
       "Epoch 724/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0829 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0989 - accuracy: 0.9833\n",
       "Epoch 725/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0827 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0987 - accuracy: 0.9833\n",
       "Epoch 726/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0827 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0986 - accuracy: 0.9800\n",
       "Epoch 727/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0825 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0983 - accuracy: 0.9800\n",
       "Epoch 728/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0823 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0982 - accuracy: 0.9800\n",
       "Epoch 729/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.0822 - accuracy: 0.9767\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0980 - accuracy: 0.9800\n",
       "Epoch 730/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.0821 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0978 - accuracy: 0.9833\n",
       "Epoch 731/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0821 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0976 - accuracy: 0.9833\n",
       "Epoch 732/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0818 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0974 - accuracy: 0.9833\n",
       "Epoch 733/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0816 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0973 - accuracy: 0.9833\n",
       "Epoch 734/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0816 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0970 - accuracy: 0.9833\n",
       "Epoch 735/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0814 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0969 - accuracy: 0.9833\n",
       "Epoch 736/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0812 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0967 - accuracy: 0.9833\n",
       "Epoch 737/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0811 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0965 - accuracy: 0.9833\n",
       "Epoch 738/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0810 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0964 - accuracy: 0.9833\n",
       "Epoch 739/1000\n",
-      "300/300 [==============================] - 0s 39us/sample - loss: 0.0808 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0962 - accuracy: 0.9833\n",
       "Epoch 740/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.0807 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0960 - accuracy: 0.9833\n",
       "Epoch 741/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0806 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0959 - accuracy: 0.9800\n",
       "Epoch 742/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0805 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0957 - accuracy: 0.9800\n",
       "Epoch 743/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0803 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0956 - accuracy: 0.9833\n",
       "Epoch 744/1000\n",
-      "300/300 [==============================] - 0s 40us/sample - loss: 0.0802 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0954 - accuracy: 0.9833\n",
       "Epoch 745/1000\n",
-      "300/300 [==============================] - 0s 42us/sample - loss: 0.0801 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0952 - accuracy: 0.9833\n",
       "Epoch 746/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.0800 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0950 - accuracy: 0.9833\n",
       "Epoch 747/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0798 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0948 - accuracy: 0.9833\n",
       "Epoch 748/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.0797 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 6ms/step - loss: 0.0948 - accuracy: 0.9833\n",
       "Epoch 749/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0796 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0946 - accuracy: 0.9800\n",
       "Epoch 750/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0795 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0943 - accuracy: 0.9833\n",
       "Epoch 751/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0794 - accuracy: 0.9800\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0941 - accuracy: 0.9800\n",
       "Epoch 752/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0792 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0940 - accuracy: 0.9833\n",
       "Epoch 753/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.0791 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0938 - accuracy: 0.9833\n",
       "Epoch 754/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0789 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0937 - accuracy: 0.9833\n",
       "Epoch 755/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0788 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0936 - accuracy: 0.9833\n",
       "Epoch 756/1000\n",
-      "300/300 [==============================] - 0s 38us/sample - loss: 0.0787 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0933 - accuracy: 0.9833\n",
       "Epoch 757/1000\n",
-      "300/300 [==============================] - 0s 41us/sample - loss: 0.0785 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0932 - accuracy: 0.9833\n",
       "Epoch 758/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.0784 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0930 - accuracy: 0.9833\n",
       "Epoch 759/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.0783 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0928 - accuracy: 0.9833\n",
       "Epoch 760/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0782 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0927 - accuracy: 0.9833\n",
       "Epoch 761/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0781 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0925 - accuracy: 0.9833\n",
       "Epoch 762/1000\n",
-      "300/300 [==============================] - 0s 41us/sample - loss: 0.0779 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.0925 - accuracy: 0.9800\n",
       "Epoch 763/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0778 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0923 - accuracy: 0.9833\n",
       "Epoch 764/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0777 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0920 - accuracy: 0.9800\n",
       "Epoch 765/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0776 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0918 - accuracy: 0.9833\n",
       "Epoch 766/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0774 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0917 - accuracy: 0.9833\n",
       "Epoch 767/1000\n",
-      "300/300 [==============================] - 0s 41us/sample - loss: 0.0773 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0916 - accuracy: 0.9833\n",
       "Epoch 768/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0772 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0914 - accuracy: 0.9833\n",
       "Epoch 769/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0773 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0913 - accuracy: 0.9833\n",
       "Epoch 770/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0770 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0911 - accuracy: 0.9833\n",
       "Epoch 771/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0769 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0909 - accuracy: 0.9833\n",
       "Epoch 772/1000\n",
-      "300/300 [==============================] - 0s 41us/sample - loss: 0.0768 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0908 - accuracy: 0.9833\n",
       "Epoch 773/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.0766 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0906 - accuracy: 0.9833\n",
       "Epoch 774/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0765 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0904 - accuracy: 0.9833\n",
       "Epoch 775/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0763 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0904 - accuracy: 0.9833\n",
       "Epoch 776/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.0763 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0901 - accuracy: 0.9833\n",
       "Epoch 777/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0761 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0900 - accuracy: 0.9833\n",
       "Epoch 778/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0760 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0898 - accuracy: 0.9833\n",
       "Epoch 779/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0759 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0896 - accuracy: 0.9833\n",
       "Epoch 780/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.0758 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0895 - accuracy: 0.9833\n",
       "Epoch 781/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0756 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0894 - accuracy: 0.9833\n",
       "Epoch 782/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0756 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0892 - accuracy: 0.9867\n",
       "Epoch 783/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0755 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0890 - accuracy: 0.9833\n",
       "Epoch 784/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0753 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0890 - accuracy: 0.9833\n",
       "Epoch 785/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0752 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0888 - accuracy: 0.9833\n",
       "Epoch 786/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0751 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0887 - accuracy: 0.9833\n",
       "Epoch 787/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0749 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0886 - accuracy: 0.9833\n",
       "Epoch 788/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.0748 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0883 - accuracy: 0.9833\n",
       "Epoch 789/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.0747 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.0882 - accuracy: 0.9833\n",
       "Epoch 790/1000\n",
-      "300/300 [==============================] - 0s 39us/sample - loss: 0.0746 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0880 - accuracy: 0.9833\n",
       "Epoch 791/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.0745 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0879 - accuracy: 0.9833\n",
       "Epoch 792/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.0744 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.0877 - accuracy: 0.9833\n",
       "Epoch 793/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.0743 - accuracy: 0.9833\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0876 - accuracy: 0.9833\n",
       "Epoch 794/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0742 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0874 - accuracy: 0.9833\n",
       "Epoch 795/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.0740 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0873 - accuracy: 0.9833\n",
       "Epoch 796/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0739 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0872 - accuracy: 0.9833\n",
       "Epoch 797/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0738 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0870 - accuracy: 0.9833\n",
       "Epoch 798/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0737 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0869 - accuracy: 0.9833\n",
       "Epoch 799/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0737 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0867 - accuracy: 0.9833\n",
       "Epoch 800/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0735 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0866 - accuracy: 0.9833\n",
       "Epoch 801/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0735 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0864 - accuracy: 0.9833\n",
       "Epoch 802/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.0732 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0863 - accuracy: 0.9833\n",
       "Epoch 803/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0731 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0861 - accuracy: 0.9833\n",
       "Epoch 804/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0730 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0860 - accuracy: 0.9833\n",
       "Epoch 805/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0729 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0858 - accuracy: 0.9833\n",
       "Epoch 806/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0728 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0857 - accuracy: 0.9833\n",
       "Epoch 807/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0727 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0855 - accuracy: 0.9833\n",
       "Epoch 808/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0726 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0854 - accuracy: 0.9833\n",
       "Epoch 809/1000\n",
-      "300/300 [==============================] - 0s 25us/sample - loss: 0.0725 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0855 - accuracy: 0.9833\n",
       "Epoch 810/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0724 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0852 - accuracy: 0.9867\n",
       "Epoch 811/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0723 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0850 - accuracy: 0.9867\n",
       "Epoch 812/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0721 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0849 - accuracy: 0.9833\n",
       "Epoch 813/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0720 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0847 - accuracy: 0.9833\n",
       "Epoch 814/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0720 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0845 - accuracy: 0.9833\n",
       "Epoch 815/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0719 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0847 - accuracy: 0.9833\n",
       "Epoch 816/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0717 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0843 - accuracy: 0.9800\n",
       "Epoch 817/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0716 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0842 - accuracy: 0.9833\n",
       "Epoch 818/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0715 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0840 - accuracy: 0.9833\n",
       "Epoch 819/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0714 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0839 - accuracy: 0.9833\n",
       "Epoch 820/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0713 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0837 - accuracy: 0.9833\n",
       "Epoch 821/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0712 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0836 - accuracy: 0.9833\n",
       "Epoch 822/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0712 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0835 - accuracy: 0.9867\n",
       "Epoch 823/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0710 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0833 - accuracy: 0.9867\n",
       "Epoch 824/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0709 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0832 - accuracy: 0.9867\n",
       "Epoch 825/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0708 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0830 - accuracy: 0.9867\n",
       "Epoch 826/1000\n",
-      "300/300 [==============================] - 0s 47us/sample - loss: 0.0707 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0830 - accuracy: 0.9833\n",
       "Epoch 827/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0706 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0828 - accuracy: 0.9833\n",
       "Epoch 828/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0705 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0827 - accuracy: 0.9833\n",
       "Epoch 829/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0704 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0825 - accuracy: 0.9833\n",
       "Epoch 830/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0703 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0825 - accuracy: 0.9867\n",
       "Epoch 831/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0702 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0823 - accuracy: 0.9867\n",
       "Epoch 832/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0701 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0822 - accuracy: 0.9867\n",
       "Epoch 833/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0701 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.0820 - accuracy: 0.9867\n",
       "Epoch 834/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0699 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 6ms/step - loss: 0.0819 - accuracy: 0.9867\n",
       "Epoch 835/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0698 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0818 - accuracy: 0.9867\n",
       "Epoch 836/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0697 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0816 - accuracy: 0.9833\n",
       "Epoch 837/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0695 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0815 - accuracy: 0.9867\n",
       "Epoch 838/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0695 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.0813 - accuracy: 0.9867\n",
       "Epoch 839/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0694 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.0813 - accuracy: 0.9833\n",
       "Epoch 840/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0692 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0811 - accuracy: 0.9833\n",
       "Epoch 841/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0691 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0810 - accuracy: 0.9833\n",
       "Epoch 842/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0691 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0808 - accuracy: 0.9867\n",
       "Epoch 843/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0689 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0807 - accuracy: 0.9867\n",
       "Epoch 844/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0689 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.0806 - accuracy: 0.9867\n",
       "Epoch 845/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0687 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0804 - accuracy: 0.9867\n",
       "Epoch 846/1000\n",
-      "300/300 [==============================] - 0s 38us/sample - loss: 0.0686 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0803 - accuracy: 0.9867\n",
       "Epoch 847/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0686 - accuracy: 0.9867\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0802 - accuracy: 0.9867\n",
       "Epoch 848/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0685 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 21ms/step - loss: 0.0801 - accuracy: 0.9867\n",
       "Epoch 849/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0683 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0800 - accuracy: 0.9867\n",
       "Epoch 850/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0683 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0799 - accuracy: 0.9867\n",
       "Epoch 851/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0681 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0798 - accuracy: 0.9867\n",
       "Epoch 852/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0681 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 23ms/step - loss: 0.0796 - accuracy: 0.9867\n",
       "Epoch 853/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0680 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0794 - accuracy: 0.9867\n",
       "Epoch 854/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0678 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0793 - accuracy: 0.9867\n",
       "Epoch 855/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0678 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0792 - accuracy: 0.9867\n",
       "Epoch 856/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.0677 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0791 - accuracy: 0.9867\n",
       "Epoch 857/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0676 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0790 - accuracy: 0.9867\n",
       "Epoch 858/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0675 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.0788 - accuracy: 0.9900\n",
       "Epoch 859/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0674 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0787 - accuracy: 0.9867\n",
       "Epoch 860/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0673 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0786 - accuracy: 0.9833\n",
       "Epoch 861/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.0672 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0785 - accuracy: 0.9833\n",
       "Epoch 862/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0672 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0783 - accuracy: 0.9867\n",
       "Epoch 863/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0670 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0783 - accuracy: 0.9867\n",
       "Epoch 864/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0669 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0781 - accuracy: 0.9867\n",
       "Epoch 865/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0668 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0780 - accuracy: 0.9867\n",
       "Epoch 866/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0667 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0779 - accuracy: 0.9867\n",
       "Epoch 867/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0666 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0777 - accuracy: 0.9867\n",
       "Epoch 868/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0665 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0777 - accuracy: 0.9867\n",
       "Epoch 869/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.0665 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0775 - accuracy: 0.9867\n",
       "Epoch 870/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0663 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0774 - accuracy: 0.9900\n",
       "Epoch 871/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0662 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0772 - accuracy: 0.9900\n",
       "Epoch 872/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0662 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0772 - accuracy: 0.9867\n",
       "Epoch 873/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0661 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.0770 - accuracy: 0.9867\n",
       "Epoch 874/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0660 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0770 - accuracy: 0.9867\n",
       "Epoch 875/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0659 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0768 - accuracy: 0.9867\n",
       "Epoch 876/1000\n",
-      "300/300 [==============================] - 0s 38us/sample - loss: 0.0658 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0766 - accuracy: 0.9867\n",
       "Epoch 877/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0657 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0765 - accuracy: 0.9867\n",
       "Epoch 878/1000\n",
-      "300/300 [==============================] - ETA: 0s - loss: 0.0914 - accuracy: 0.99 - 0s 35us/sample - loss: 0.0656 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0765 - accuracy: 0.9867\n",
       "Epoch 879/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0655 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0763 - accuracy: 0.9867\n",
       "Epoch 880/1000\n",
-      "300/300 [==============================] - ETA: 0s - loss: 0.0841 - accuracy: 0.98 - 0s 34us/sample - loss: 0.0655 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0763 - accuracy: 0.9867\n",
       "Epoch 881/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0654 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0761 - accuracy: 0.9900\n",
       "Epoch 882/1000\n",
-      "300/300 [==============================] - 0s 37us/sample - loss: 0.0652 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0760 - accuracy: 0.9900\n",
       "Epoch 883/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.0652 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0759 - accuracy: 0.9867\n",
       "Epoch 884/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0651 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0757 - accuracy: 0.9867\n",
       "Epoch 885/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0650 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0757 - accuracy: 0.9867\n",
       "Epoch 886/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0649 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0755 - accuracy: 0.9867\n",
       "Epoch 887/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0648 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0754 - accuracy: 0.9867\n",
       "Epoch 888/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0647 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.0754 - accuracy: 0.9867\n",
       "Epoch 889/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0647 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0752 - accuracy: 0.9900\n",
       "Epoch 890/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0646 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0751 - accuracy: 0.9900\n",
       "Epoch 891/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0644 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0750 - accuracy: 0.9900\n",
       "Epoch 892/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.0644 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 12ms/step - loss: 0.0748 - accuracy: 0.9900\n",
       "Epoch 893/1000\n",
-      "300/300 [==============================] - 0s 38us/sample - loss: 0.0643 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0748 - accuracy: 0.9867\n",
       "Epoch 894/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0642 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0747 - accuracy: 0.9867\n",
       "Epoch 895/1000\n",
-      "300/300 [==============================] - 0s 38us/sample - loss: 0.0641 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0745 - accuracy: 0.9867\n",
       "Epoch 896/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.0640 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0744 - accuracy: 0.9867\n",
       "Epoch 897/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0639 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0743 - accuracy: 0.9833\n",
       "Epoch 898/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0638 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0742 - accuracy: 0.9900\n",
       "Epoch 899/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0638 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0740 - accuracy: 0.9900\n",
       "Epoch 900/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0637 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0740 - accuracy: 0.9900\n",
       "Epoch 901/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0636 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0739 - accuracy: 0.9900\n",
       "Epoch 902/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0635 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0738 - accuracy: 0.9900\n",
       "Epoch 903/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0635 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0737 - accuracy: 0.9900\n",
       "Epoch 904/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0633 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0735 - accuracy: 0.9900\n",
       "Epoch 905/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0633 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0737 - accuracy: 0.9867\n",
       "Epoch 906/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0632 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0734 - accuracy: 0.9867\n",
       "Epoch 907/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0631 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0733 - accuracy: 0.9900\n",
       "Epoch 908/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0630 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0731 - accuracy: 0.9900\n",
       "Epoch 909/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0630 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0730 - accuracy: 0.9900\n",
       "Epoch 910/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0629 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0729 - accuracy: 0.9900\n",
       "Epoch 911/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0628 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0728 - accuracy: 0.9900\n",
       "Epoch 912/1000\n",
-      "300/300 [==============================] - 0s 50us/sample - loss: 0.0627 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0727 - accuracy: 0.9900\n",
       "Epoch 913/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0626 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0726 - accuracy: 0.9900\n",
       "Epoch 914/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0625 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.0725 - accuracy: 0.9900\n",
       "Epoch 915/1000\n",
-      "300/300 [==============================] - 0s 25us/sample - loss: 0.0624 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0724 - accuracy: 0.9900\n",
       "Epoch 916/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0623 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0723 - accuracy: 0.9867\n",
       "Epoch 917/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0622 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0722 - accuracy: 0.9900\n",
       "Epoch 918/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0622 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0721 - accuracy: 0.9900\n",
       "Epoch 919/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0621 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0719 - accuracy: 0.9900\n",
       "Epoch 920/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0620 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0718 - accuracy: 0.9900\n",
       "Epoch 921/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0620 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0718 - accuracy: 0.9900\n",
       "Epoch 922/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0618 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0717 - accuracy: 0.9900\n",
       "Epoch 923/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0618 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 6ms/step - loss: 0.0716 - accuracy: 0.9900\n",
       "Epoch 924/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0616 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0715 - accuracy: 0.9833\n",
       "Epoch 925/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0616 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0713 - accuracy: 0.9867\n",
       "Epoch 926/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0615 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0713 - accuracy: 0.9867\n",
       "Epoch 927/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0614 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0711 - accuracy: 0.9867\n",
       "Epoch 928/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.0613 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0710 - accuracy: 0.9900\n",
       "Epoch 929/1000\n",
-      "300/300 [==============================] - 0s 25us/sample - loss: 0.0613 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0709 - accuracy: 0.9900\n",
       "Epoch 930/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0612 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0708 - accuracy: 0.9900\n",
       "Epoch 931/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0612 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0708 - accuracy: 0.9900\n",
       "Epoch 932/1000\n",
-      "300/300 [==============================] - 0s 25us/sample - loss: 0.0610 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0706 - accuracy: 0.9900\n",
       "Epoch 933/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0610 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0705 - accuracy: 0.9900\n",
       "Epoch 934/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0609 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0704 - accuracy: 0.9900\n",
       "Epoch 935/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0608 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0703 - accuracy: 0.9900\n",
       "Epoch 936/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0609 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0702 - accuracy: 0.9900\n",
       "Epoch 937/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0606 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0701 - accuracy: 0.9900\n",
       "Epoch 938/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0606 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0701 - accuracy: 0.9900\n",
       "Epoch 939/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0605 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0699 - accuracy: 0.9867\n",
       "Epoch 940/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0604 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0699 - accuracy: 0.9900\n",
       "Epoch 941/1000\n",
-      "300/300 [==============================] - 0s 25us/sample - loss: 0.0603 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0697 - accuracy: 0.9900\n",
       "Epoch 942/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0602 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0696 - accuracy: 0.9900\n",
       "Epoch 943/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0602 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0696 - accuracy: 0.9900\n",
       "Epoch 944/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0601 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0694 - accuracy: 0.9900\n",
       "Epoch 945/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0600 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0693 - accuracy: 0.9900\n",
       "Epoch 946/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0600 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0694 - accuracy: 0.9867\n",
       "Epoch 947/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0599 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0691 - accuracy: 0.9900\n",
       "Epoch 948/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0598 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0690 - accuracy: 0.9900\n",
       "Epoch 949/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0597 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0690 - accuracy: 0.9867\n",
       "Epoch 950/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0596 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0689 - accuracy: 0.9900\n",
       "Epoch 951/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0595 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0688 - accuracy: 0.9900\n",
       "Epoch 952/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0595 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0687 - accuracy: 0.9900\n",
       "Epoch 953/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0594 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0686 - accuracy: 0.9900\n",
       "Epoch 954/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0593 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0685 - accuracy: 0.9900\n",
       "Epoch 955/1000\n",
-      "300/300 [==============================] - 0s 41us/sample - loss: 0.0593 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0685 - accuracy: 0.9900\n",
       "Epoch 956/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0592 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0684 - accuracy: 0.9900\n",
       "Epoch 957/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0591 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0683 - accuracy: 0.9900\n",
       "Epoch 958/1000\n",
-      "300/300 [==============================] - 0s 36us/sample - loss: 0.0590 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0681 - accuracy: 0.9900\n",
       "Epoch 959/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0590 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0680 - accuracy: 0.9900\n",
       "Epoch 960/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0589 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0679 - accuracy: 0.9867\n",
       "Epoch 961/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0589 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0679 - accuracy: 0.9900\n",
       "Epoch 962/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0587 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0677 - accuracy: 0.9900\n",
       "Epoch 963/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0586 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0678 - accuracy: 0.9867\n",
       "Epoch 964/1000\n",
-      "300/300 [==============================] - 0s 35us/sample - loss: 0.0586 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0675 - accuracy: 0.9900\n",
       "Epoch 965/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0585 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0675 - accuracy: 0.9900\n",
       "Epoch 966/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0585 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0674 - accuracy: 0.9900\n",
       "Epoch 967/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0584 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0673 - accuracy: 0.9867\n",
       "Epoch 968/1000\n",
-      "300/300 [==============================] - 0s 34us/sample - loss: 0.0583 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0672 - accuracy: 0.9900\n",
       "Epoch 969/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0582 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0671 - accuracy: 0.9900\n",
       "Epoch 970/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0581 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0670 - accuracy: 0.9900\n",
       "Epoch 971/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0580 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0670 - accuracy: 0.9900\n",
       "Epoch 972/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0580 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0670 - accuracy: 0.9900\n",
       "Epoch 973/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0579 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0667 - accuracy: 0.9900\n",
       "Epoch 974/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0579 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0667 - accuracy: 0.9900\n",
       "Epoch 975/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0578 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0666 - accuracy: 0.9900\n",
       "Epoch 976/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0577 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0664 - accuracy: 0.9900\n",
       "Epoch 977/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0577 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0665 - accuracy: 0.9900\n",
       "Epoch 978/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0575 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0664 - accuracy: 0.9900\n",
       "Epoch 979/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0575 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0662 - accuracy: 0.9900\n",
       "Epoch 980/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0574 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0661 - accuracy: 0.9900\n",
       "Epoch 981/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0573 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 6ms/step - loss: 0.0660 - accuracy: 0.9900\n",
       "Epoch 982/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0573 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.0659 - accuracy: 0.9900\n",
       "Epoch 983/1000\n",
-      "300/300 [==============================] - 0s 41us/sample - loss: 0.0572 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0659 - accuracy: 0.9900\n",
       "Epoch 984/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0571 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0658 - accuracy: 0.9900\n",
       "Epoch 985/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0571 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0657 - accuracy: 0.9900\n",
       "Epoch 986/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0570 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0657 - accuracy: 0.9900\n",
       "Epoch 987/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0569 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0655 - accuracy: 0.9867\n",
       "Epoch 988/1000\n",
-      "300/300 [==============================] - 0s 28us/sample - loss: 0.0569 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0654 - accuracy: 0.9900\n",
       "Epoch 989/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0568 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0653 - accuracy: 0.9900\n",
       "Epoch 990/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0567 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0653 - accuracy: 0.9867\n",
       "Epoch 991/1000\n",
-      "300/300 [==============================] - 0s 29us/sample - loss: 0.0567 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0652 - accuracy: 0.9867\n",
       "Epoch 992/1000\n",
-      "300/300 [==============================] - 0s 31us/sample - loss: 0.0566 - accuracy: 0.9933\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0651 - accuracy: 0.9900\n",
       "Epoch 993/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0565 - accuracy: 0.9933\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0650 - accuracy: 0.9900\n",
       "Epoch 994/1000\n",
-      "300/300 [==============================] - 0s 30us/sample - loss: 0.0564 - accuracy: 0.9933\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0649 - accuracy: 0.9900\n",
       "Epoch 995/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0564 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 5ms/step - loss: 0.0649 - accuracy: 0.9900\n",
       "Epoch 996/1000\n",
-      "300/300 [==============================] - 0s 33us/sample - loss: 0.0564 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0647 - accuracy: 0.9900\n",
       "Epoch 997/1000\n",
-      "300/300 [==============================] - 0s 26us/sample - loss: 0.0562 - accuracy: 0.9933\n",
+      "3/3 [==============================] - 0s 4ms/step - loss: 0.0646 - accuracy: 0.9900\n",
       "Epoch 998/1000\n",
-      "300/300 [==============================] - 0s 27us/sample - loss: 0.0562 - accuracy: 0.9900\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0645 - accuracy: 0.9900\n",
       "Epoch 999/1000\n",
-      "300/300 [==============================] - 0s 32us/sample - loss: 0.0561 - accuracy: 0.9933\n",
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0646 - accuracy: 0.9867\n",
       "Epoch 1000/1000\n",
-      "300/300 [==============================] - 0s 25us/sample - loss: 0.0560 - accuracy: 0.9900\n"
+      "3/3 [==============================] - 0s 3ms/step - loss: 0.0644 - accuracy: 0.9900\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "<tensorflow.python.keras.callbacks.History at 0x7fce0861a110>"
+       "<keras.callbacks.History at 0x7f472477ad50>"
       ]
      },
-     "execution_count": 25,
+     "execution_count": 30,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3299,15 +3299,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "300/300 [==============================] - 0s 383us/sample - loss: 0.0559 - accuracy: 0.9900\n",
-      "Accuracy on test dataset: 0.99\n"
+      "10/10 [==============================] - 0s 2ms/step - loss: 0.0643 - accuracy: 0.9900\n",
+      "Accuracy on test dataset: 0.9900000095367432\n"
      ]
     }
    ],
@@ -3325,62 +3325,62 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Requirement already satisfied: tensorflow-datasets in /opt/conda/lib/python3.7/site-packages (4.1.0)\n",
-      "Requirement already satisfied: future in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (0.18.2)\n",
+      "Requirement already satisfied: tensorflow-datasets in /opt/conda/lib/python3.7/site-packages (4.5.2)\n",
+      "Requirement already satisfied: dill in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (0.3.4)\n",
+      "Requirement already satisfied: absl-py in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (1.0.0)\n",
       "Requirement already satisfied: numpy in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (1.19.1)\n",
-      "Requirement already satisfied: tqdm in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (4.45.0)\n",
-      "Requirement already satisfied: importlib-resources; python_version < \"3.9\" in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (3.3.0)\n",
+      "Requirement already satisfied: tensorflow-metadata in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (1.6.0)\n",
+      "Requirement already satisfied: typing-extensions; python_version < \"3.8\" in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (3.7.4.3)\n",
       "Requirement already satisfied: promise in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (2.3)\n",
       "Requirement already satisfied: six in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (1.14.0)\n",
-      "Requirement already satisfied: attrs>=18.1.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (19.3.0)\n",
-      "Requirement already satisfied: absl-py in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (0.11.0)\n",
+      "Requirement already satisfied: importlib-resources; python_version < \"3.9\" in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (5.4.0)\n",
+      "Requirement already satisfied: tqdm in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (4.45.0)\n",
       "Requirement already satisfied: requests>=2.19.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (2.23.0)\n",
+      "Requirement already satisfied: protobuf>=3.12.2 in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (3.19.4)\n",
       "Requirement already satisfied: termcolor in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (1.1.0)\n",
-      "Requirement already satisfied: typing-extensions; python_version < \"3.8\" in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (3.7.4.3)\n",
-      "Requirement already satisfied: tensorflow-metadata in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (0.25.0)\n",
-      "Requirement already satisfied: dill in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (0.3.3)\n",
-      "Requirement already satisfied: protobuf>=3.6.1 in /opt/conda/lib/python3.7/site-packages (from tensorflow-datasets) (3.14.0)\n",
-      "Requirement already satisfied: zipp>=0.4; python_version < \"3.8\" in /opt/conda/lib/python3.7/site-packages (from importlib-resources; python_version < \"3.9\"->tensorflow-datasets) (3.1.0)\n",
-      "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tensorflow-datasets) (2020.11.8)\n",
+      "Requirement already satisfied: googleapis-common-protos<2,>=1.52.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow-metadata->tensorflow-datasets) (1.55.0)\n",
+      "Requirement already satisfied: zipp>=3.1.0; python_version < \"3.10\" in /opt/conda/lib/python3.7/site-packages (from importlib-resources; python_version < \"3.9\"->tensorflow-datasets) (3.1.0)\n",
+      "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tensorflow-datasets) (1.25.9)\n",
       "Requirement already satisfied: idna<3,>=2.5 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tensorflow-datasets) (2.9)\n",
       "Requirement already satisfied: chardet<4,>=3.0.2 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tensorflow-datasets) (3.0.4)\n",
-      "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tensorflow-datasets) (1.25.9)\n",
-      "Requirement already satisfied: googleapis-common-protos<2,>=1.52.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow-metadata->tensorflow-datasets) (1.52.0)\n",
-      "\u001b[33mWARNING: You are using pip version 20.1.1; however, version 20.3.1 is available.\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tensorflow-datasets) (2020.6.20)\n",
+      "\u001b[33mWARNING: You are using pip version 20.2.4; however, version 22.0.3 is available.\n",
       "You should consider upgrading via the '/opt/conda/bin/python3 -m pip install --upgrade pip' command.\u001b[0m\n",
       "Collecting tfds-nightly\n",
-      "  Downloading tfds_nightly-4.1.0.dev202012090106-py3-none-any.whl (3.7 MB)\n",
-      "\u001b[K     |████████████████████████████████| 3.7 MB 417 kB/s eta 0:00:01\n",
-      "\u001b[?25hRequirement already satisfied: tqdm in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (4.45.0)\n",
-      "Requirement already satisfied: importlib-resources; python_version < \"3.9\" in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (3.3.0)\n",
-      "Requirement already satisfied: six in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (1.14.0)\n",
-      "Requirement already satisfied: typing-extensions; python_version < \"3.8\" in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (3.7.4.3)\n",
+      "  Downloading tfds_nightly-4.5.2.dev202202240044-py3-none-any.whl (4.2 MB)\n",
+      "\u001b[K     |████████████████████████████████| 4.2 MB 5.1 MB/s eta 0:00:01\n",
+      "\u001b[?25hRequirement already satisfied: protobuf>=3.12.2 in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (3.19.4)\n",
+      "Requirement already satisfied: numpy in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (1.19.1)\n",
       "Requirement already satisfied: termcolor in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (1.1.0)\n",
-      "Requirement already satisfied: attrs>=18.1.0 in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (19.3.0)\n",
-      "Requirement already satisfied: absl-py in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (0.11.0)\n",
+      "Requirement already satisfied: tensorflow-metadata in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (1.6.0)\n",
+      "Collecting etils[epath-no-tf]\n",
+      "  Downloading etils-0.4.0-py3-none-any.whl (76 kB)\n",
+      "\u001b[K     |████████████████████████████████| 76 kB 2.2 MB/s  eta 0:00:01\n",
+      "\u001b[?25hRequirement already satisfied: dill in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (0.3.4)\n",
       "Requirement already satisfied: requests>=2.19.0 in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (2.23.0)\n",
-      "Requirement already satisfied: dill in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (0.3.3)\n",
-      "Requirement already satisfied: future in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (0.18.2)\n",
-      "Requirement already satisfied: protobuf>=3.12.2 in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (3.14.0)\n",
-      "Requirement already satisfied: tensorflow-metadata in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (0.25.0)\n",
+      "Requirement already satisfied: toml in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (0.10.2)\n",
+      "Requirement already satisfied: absl-py in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (1.0.0)\n",
+      "Requirement already satisfied: six in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (1.14.0)\n",
+      "Requirement already satisfied: importlib-resources; python_version < \"3.9\" in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (5.4.0)\n",
+      "Requirement already satisfied: typing-extensions; python_version < \"3.8\" in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (3.7.4.3)\n",
+      "Requirement already satisfied: tqdm in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (4.45.0)\n",
       "Requirement already satisfied: promise in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (2.3)\n",
-      "Requirement already satisfied: numpy in /opt/conda/lib/python3.7/site-packages (from tfds-nightly) (1.19.1)\n",
-      "Requirement already satisfied: zipp>=0.4; python_version < \"3.8\" in /opt/conda/lib/python3.7/site-packages (from importlib-resources; python_version < \"3.9\"->tfds-nightly) (3.1.0)\n",
+      "Requirement already satisfied: googleapis-common-protos<2,>=1.52.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow-metadata->tfds-nightly) (1.55.0)\n",
+      "Requirement already satisfied: zipp; extra == \"epath-no-tf\" in /opt/conda/lib/python3.7/site-packages (from etils[epath-no-tf]->tfds-nightly) (3.1.0)\n",
+      "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tfds-nightly) (1.25.9)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tfds-nightly) (2020.6.20)\n",
       "Requirement already satisfied: chardet<4,>=3.0.2 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tfds-nightly) (3.0.4)\n",
       "Requirement already satisfied: idna<3,>=2.5 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tfds-nightly) (2.9)\n",
-      "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tfds-nightly) (1.25.9)\n",
-      "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.7/site-packages (from requests>=2.19.0->tfds-nightly) (2020.11.8)\n",
-      "Requirement already satisfied: googleapis-common-protos<2,>=1.52.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow-metadata->tfds-nightly) (1.52.0)\n",
-      "Installing collected packages: tfds-nightly\n",
-      "Successfully installed tfds-nightly-4.1.0.dev202012090106\n",
-      "\u001b[33mWARNING: You are using pip version 20.1.1; however, version 20.3.1 is available.\n",
+      "Installing collected packages: etils, tfds-nightly\n",
+      "Successfully installed etils-0.4.0 tfds-nightly-4.5.2.dev202202240044\n",
+      "\u001b[33mWARNING: You are using pip version 20.2.4; however, version 22.0.3 is available.\n",
       "You should consider upgrading via the '/opt/conda/bin/python3 -m pip install --upgrade pip' command.\u001b[0m\n"
      ]
     }
@@ -3392,14 +3392,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 33,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2.1.0\n"
+      "2.7.1\n"
      ]
     }
    ],
@@ -3423,7 +3423,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3434,7 +3434,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 35,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3444,7 +3444,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 36,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3454,7 +3454,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 37,
    "metadata": {},
    "outputs": [
     {
@@ -3475,7 +3475,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 38,
    "metadata": {},
    "outputs": [
     {
@@ -3519,7 +3519,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 39,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3564,7 +3564,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 40,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -3575,22 +3575,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 41,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Model: \"sequential_1\"\n",
+      "Model: \"sequential_3\"\n",
       "_________________________________________________________________\n",
-      "Layer (type)                 Output Shape              Param #   \n",
+      " Layer (type)                Output Shape              Param #   \n",
       "=================================================================\n",
-      "dense_2 (Dense)              (None, 500)               392500    \n",
-      "_________________________________________________________________\n",
-      "dense_3 (Dense)              (None, 50)                25050     \n",
-      "_________________________________________________________________\n",
-      "dense_4 (Dense)              (None, 10)                510       \n",
+      " dense_6 (Dense)             (None, 500)               392500    \n",
+      "                                                                 \n",
+      " dense_7 (Dense)             (None, 50)                25050     \n",
+      "                                                                 \n",
+      " dense_8 (Dense)             (None, 10)                510       \n",
+      "                                                                 \n",
       "=================================================================\n",
       "Total params: 418,060\n",
       "Trainable params: 418,060\n",
@@ -3619,7 +3620,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 42,
    "metadata": {},
    "outputs": [
     {
@@ -3628,9 +3629,9 @@
      "text": [
       "(3000, 784)\n",
       "(3000, 10)\n",
-      "2000/2000 [==============================] - 0s 142us/sample - loss: 2.4531 - accuracy: 0.1205\n",
-      "Accuracy : 0.1205\n",
-      "Loss : 2.4530571994781494\n"
+      "63/63 [==============================] - 1s 3ms/step - loss: 2.5060 - accuracy: 0.1035\n",
+      "Accuracy : 0.10350000113248825\n",
+      "Loss : 2.5059869289398193\n"
      ]
     }
    ],
@@ -3649,406 +3650,613 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 43,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Train on 2400 samples, validate on 600 samples\n",
       "Epoch 1/300\n",
-      "2400/2400 [==============================] - 1s 321us/sample - loss: 2.4392 - accuracy: 0.1271 - val_loss: 2.4648 - val_accuracy: 0.1033\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.5072 - accuracy: 0.1054 - val_loss: 2.4629 - val_accuracy: 0.1000\n",
       "Epoch 2/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 2.4292 - accuracy: 0.1304 - val_loss: 2.4558 - val_accuracy: 0.1050\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.4977 - accuracy: 0.1050 - val_loss: 2.4551 - val_accuracy: 0.1033\n",
       "Epoch 3/300\n",
-      "2400/2400 [==============================] - 0s 179us/sample - loss: 2.4198 - accuracy: 0.1329 - val_loss: 2.4472 - val_accuracy: 0.1067\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.4888 - accuracy: 0.1063 - val_loss: 2.4477 - val_accuracy: 0.1033\n",
       "Epoch 4/300\n",
-      "2400/2400 [==============================] - 0s 181us/sample - loss: 2.4108 - accuracy: 0.1354 - val_loss: 2.4389 - val_accuracy: 0.1067\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.4803 - accuracy: 0.1079 - val_loss: 2.4405 - val_accuracy: 0.1050\n",
       "Epoch 5/300\n",
-      "2400/2400 [==============================] - 0s 188us/sample - loss: 2.4021 - accuracy: 0.1379 - val_loss: 2.4308 - val_accuracy: 0.1050\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.4720 - accuracy: 0.1100 - val_loss: 2.4335 - val_accuracy: 0.1083\n",
       "Epoch 6/300\n",
-      "2400/2400 [==============================] - 0s 176us/sample - loss: 2.3936 - accuracy: 0.1408 - val_loss: 2.4229 - val_accuracy: 0.1067\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.4639 - accuracy: 0.1100 - val_loss: 2.4266 - val_accuracy: 0.1100\n",
       "Epoch 7/300\n",
-      "2400/2400 [==============================] - 0s 184us/sample - loss: 2.3854 - accuracy: 0.1429 - val_loss: 2.4153 - val_accuracy: 0.1067\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 2.4561 - accuracy: 0.1108 - val_loss: 2.4200 - val_accuracy: 0.1100\n",
       "Epoch 8/300\n",
-      "2400/2400 [==============================] - 0s 174us/sample - loss: 2.3774 - accuracy: 0.1450 - val_loss: 2.4079 - val_accuracy: 0.1117\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.4484 - accuracy: 0.1112 - val_loss: 2.4135 - val_accuracy: 0.1133\n",
       "Epoch 9/300\n",
-      "2400/2400 [==============================] - 0s 171us/sample - loss: 2.3697 - accuracy: 0.1462 - val_loss: 2.4007 - val_accuracy: 0.1117\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.4408 - accuracy: 0.1129 - val_loss: 2.4071 - val_accuracy: 0.1133\n",
       "Epoch 10/300\n",
-      "2400/2400 [==============================] - 0s 189us/sample - loss: 2.3622 - accuracy: 0.1479 - val_loss: 2.3937 - val_accuracy: 0.1117\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.4334 - accuracy: 0.1146 - val_loss: 2.4008 - val_accuracy: 0.1167\n",
       "Epoch 11/300\n",
-      "2400/2400 [==============================] - 0s 172us/sample - loss: 2.3548 - accuracy: 0.1488 - val_loss: 2.3868 - val_accuracy: 0.1117\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.4262 - accuracy: 0.1150 - val_loss: 2.3946 - val_accuracy: 0.1183\n",
       "Epoch 12/300\n",
-      "2400/2400 [==============================] - 0s 173us/sample - loss: 2.3476 - accuracy: 0.1492 - val_loss: 2.3801 - val_accuracy: 0.1133\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.4191 - accuracy: 0.1167 - val_loss: 2.3886 - val_accuracy: 0.1183\n",
       "Epoch 13/300\n",
-      "2400/2400 [==============================] - 0s 174us/sample - loss: 2.3407 - accuracy: 0.1513 - val_loss: 2.3736 - val_accuracy: 0.1150\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.4122 - accuracy: 0.1179 - val_loss: 2.3828 - val_accuracy: 0.1167\n",
       "Epoch 14/300\n",
-      "2400/2400 [==============================] - 0s 179us/sample - loss: 2.3339 - accuracy: 0.1521 - val_loss: 2.3673 - val_accuracy: 0.1150\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.4054 - accuracy: 0.1183 - val_loss: 2.3771 - val_accuracy: 0.1183\n",
       "Epoch 15/300\n",
-      "2400/2400 [==============================] - 0s 174us/sample - loss: 2.3273 - accuracy: 0.1529 - val_loss: 2.3611 - val_accuracy: 0.1183\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.3988 - accuracy: 0.1196 - val_loss: 2.3714 - val_accuracy: 0.1183\n",
       "Epoch 16/300\n",
-      "2400/2400 [==============================] - 0s 175us/sample - loss: 2.3209 - accuracy: 0.1554 - val_loss: 2.3552 - val_accuracy: 0.1217\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.3923 - accuracy: 0.1200 - val_loss: 2.3659 - val_accuracy: 0.1233\n",
       "Epoch 17/300\n",
-      "2400/2400 [==============================] - 0s 174us/sample - loss: 2.3146 - accuracy: 0.1567 - val_loss: 2.3494 - val_accuracy: 0.1217\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.3859 - accuracy: 0.1208 - val_loss: 2.3605 - val_accuracy: 0.1267\n",
       "Epoch 18/300\n",
-      "2400/2400 [==============================] - 0s 173us/sample - loss: 2.3085 - accuracy: 0.1592 - val_loss: 2.3438 - val_accuracy: 0.1233\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.3797 - accuracy: 0.1225 - val_loss: 2.3552 - val_accuracy: 0.1267\n",
       "Epoch 19/300\n",
-      "2400/2400 [==============================] - 0s 179us/sample - loss: 2.3026 - accuracy: 0.1629 - val_loss: 2.3383 - val_accuracy: 0.1250\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.3735 - accuracy: 0.1238 - val_loss: 2.3499 - val_accuracy: 0.1283\n",
       "Epoch 20/300\n",
-      "2400/2400 [==============================] - 0s 180us/sample - loss: 2.2969 - accuracy: 0.1642 - val_loss: 2.3330 - val_accuracy: 0.1283\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 2.3674 - accuracy: 0.1254 - val_loss: 2.3448 - val_accuracy: 0.1300\n",
       "Epoch 21/300\n",
-      "2400/2400 [==============================] - 0s 168us/sample - loss: 2.2913 - accuracy: 0.1667 - val_loss: 2.3279 - val_accuracy: 0.1333\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 2.3615 - accuracy: 0.1271 - val_loss: 2.3397 - val_accuracy: 0.1300\n",
       "Epoch 22/300\n",
-      "2400/2400 [==============================] - 0s 139us/sample - loss: 2.2859 - accuracy: 0.1688 - val_loss: 2.3229 - val_accuracy: 0.1333\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.3556 - accuracy: 0.1283 - val_loss: 2.3348 - val_accuracy: 0.1300\n",
       "Epoch 23/300\n",
-      "2400/2400 [==============================] - 0s 156us/sample - loss: 2.2806 - accuracy: 0.1717 - val_loss: 2.3180 - val_accuracy: 0.1350\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.3498 - accuracy: 0.1304 - val_loss: 2.3299 - val_accuracy: 0.1333\n",
       "Epoch 24/300\n",
-      "2400/2400 [==============================] - 0s 165us/sample - loss: 2.2754 - accuracy: 0.1762 - val_loss: 2.3132 - val_accuracy: 0.1367\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 2.3442 - accuracy: 0.1308 - val_loss: 2.3252 - val_accuracy: 0.1333\n",
       "Epoch 25/300\n",
-      "2400/2400 [==============================] - 0s 169us/sample - loss: 2.2703 - accuracy: 0.1783 - val_loss: 2.3085 - val_accuracy: 0.1450\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.3386 - accuracy: 0.1308 - val_loss: 2.3205 - val_accuracy: 0.1333\n",
       "Epoch 26/300\n",
-      "2400/2400 [==============================] - 0s 176us/sample - loss: 2.2654 - accuracy: 0.1808 - val_loss: 2.3040 - val_accuracy: 0.1467\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.3331 - accuracy: 0.1325 - val_loss: 2.3160 - val_accuracy: 0.1367\n",
       "Epoch 27/300\n",
-      "2400/2400 [==============================] - 0s 146us/sample - loss: 2.2606 - accuracy: 0.1838 - val_loss: 2.2995 - val_accuracy: 0.1483\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 2.3278 - accuracy: 0.1338 - val_loss: 2.3115 - val_accuracy: 0.1367\n",
       "Epoch 28/300\n",
-      "2400/2400 [==============================] - 0s 163us/sample - loss: 2.2558 - accuracy: 0.1871 - val_loss: 2.2952 - val_accuracy: 0.1517\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 2.3225 - accuracy: 0.1342 - val_loss: 2.3071 - val_accuracy: 0.1400\n",
       "Epoch 29/300\n",
-      "2400/2400 [==============================] - 0s 153us/sample - loss: 2.2512 - accuracy: 0.1921 - val_loss: 2.2909 - val_accuracy: 0.1533\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.3173 - accuracy: 0.1350 - val_loss: 2.3028 - val_accuracy: 0.1400\n",
       "Epoch 30/300\n",
-      "2400/2400 [==============================] - 0s 157us/sample - loss: 2.2467 - accuracy: 0.1937 - val_loss: 2.2868 - val_accuracy: 0.1550\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.3122 - accuracy: 0.1379 - val_loss: 2.2985 - val_accuracy: 0.1433\n",
       "Epoch 31/300\n",
-      "2400/2400 [==============================] - 0s 169us/sample - loss: 2.2422 - accuracy: 0.1975 - val_loss: 2.2827 - val_accuracy: 0.1550\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.3072 - accuracy: 0.1388 - val_loss: 2.2943 - val_accuracy: 0.1417\n",
       "Epoch 32/300\n",
-      "2400/2400 [==============================] - 0s 159us/sample - loss: 2.2379 - accuracy: 0.2013 - val_loss: 2.2787 - val_accuracy: 0.1617\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.3023 - accuracy: 0.1412 - val_loss: 2.2902 - val_accuracy: 0.1417\n",
       "Epoch 33/300\n",
-      "2400/2400 [==============================] - 0s 161us/sample - loss: 2.2336 - accuracy: 0.2042 - val_loss: 2.2748 - val_accuracy: 0.1667\n",
+      "75/75 [==============================] - 1s 10ms/step - loss: 2.2974 - accuracy: 0.1429 - val_loss: 2.2862 - val_accuracy: 0.1400\n",
       "Epoch 34/300\n",
-      "2400/2400 [==============================] - 0s 147us/sample - loss: 2.2294 - accuracy: 0.2096 - val_loss: 2.2709 - val_accuracy: 0.1733\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2926 - accuracy: 0.1446 - val_loss: 2.2822 - val_accuracy: 0.1417\n",
       "Epoch 35/300\n",
-      "2400/2400 [==============================] - 0s 162us/sample - loss: 2.2254 - accuracy: 0.2121 - val_loss: 2.2672 - val_accuracy: 0.1750\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 2.2879 - accuracy: 0.1471 - val_loss: 2.2783 - val_accuracy: 0.1383\n",
       "Epoch 36/300\n",
-      "2400/2400 [==============================] - 0s 169us/sample - loss: 2.2213 - accuracy: 0.2138 - val_loss: 2.2635 - val_accuracy: 0.1850\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 2.2833 - accuracy: 0.1488 - val_loss: 2.2745 - val_accuracy: 0.1400\n",
       "Epoch 37/300\n",
-      "2400/2400 [==============================] - 0s 170us/sample - loss: 2.2174 - accuracy: 0.2188 - val_loss: 2.2598 - val_accuracy: 0.1867\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2787 - accuracy: 0.1521 - val_loss: 2.2707 - val_accuracy: 0.1400\n",
       "Epoch 38/300\n",
-      "2400/2400 [==============================] - 0s 180us/sample - loss: 2.2135 - accuracy: 0.2237 - val_loss: 2.2563 - val_accuracy: 0.1900\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2742 - accuracy: 0.1554 - val_loss: 2.2670 - val_accuracy: 0.1400\n",
       "Epoch 39/300\n",
-      "2400/2400 [==============================] - 0s 163us/sample - loss: 2.2097 - accuracy: 0.2271 - val_loss: 2.2528 - val_accuracy: 0.1983\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2698 - accuracy: 0.1554 - val_loss: 2.2633 - val_accuracy: 0.1400\n",
       "Epoch 40/300\n",
-      "2400/2400 [==============================] - 0s 169us/sample - loss: 2.2059 - accuracy: 0.2325 - val_loss: 2.2494 - val_accuracy: 0.2017\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 2.2654 - accuracy: 0.1562 - val_loss: 2.2597 - val_accuracy: 0.1417\n",
       "Epoch 41/300\n",
-      "2400/2400 [==============================] - 0s 179us/sample - loss: 2.2022 - accuracy: 0.2362 - val_loss: 2.2460 - val_accuracy: 0.2100\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2611 - accuracy: 0.1579 - val_loss: 2.2562 - val_accuracy: 0.1450\n",
       "Epoch 42/300\n",
-      "2400/2400 [==============================] - 0s 176us/sample - loss: 2.1986 - accuracy: 0.2404 - val_loss: 2.2427 - val_accuracy: 0.2183\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2569 - accuracy: 0.1587 - val_loss: 2.2527 - val_accuracy: 0.1450\n",
       "Epoch 43/300\n",
-      "2400/2400 [==============================] - 0s 168us/sample - loss: 2.1950 - accuracy: 0.2446 - val_loss: 2.2395 - val_accuracy: 0.2217\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2527 - accuracy: 0.1612 - val_loss: 2.2492 - val_accuracy: 0.1450\n",
       "Epoch 44/300\n",
-      "2400/2400 [==============================] - 0s 189us/sample - loss: 2.1914 - accuracy: 0.2525 - val_loss: 2.2363 - val_accuracy: 0.2250\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2486 - accuracy: 0.1637 - val_loss: 2.2458 - val_accuracy: 0.1483\n",
       "Epoch 45/300\n",
-      "2400/2400 [==============================] - 0s 181us/sample - loss: 2.1880 - accuracy: 0.2575 - val_loss: 2.2332 - val_accuracy: 0.2283\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2445 - accuracy: 0.1663 - val_loss: 2.2424 - val_accuracy: 0.1500\n",
       "Epoch 46/300\n",
-      "2400/2400 [==============================] - 0s 168us/sample - loss: 2.1846 - accuracy: 0.2625 - val_loss: 2.2301 - val_accuracy: 0.2333\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 2.2404 - accuracy: 0.1671 - val_loss: 2.2391 - val_accuracy: 0.1550\n",
       "Epoch 47/300\n",
-      "2400/2400 [==============================] - 0s 166us/sample - loss: 2.1812 - accuracy: 0.2717 - val_loss: 2.2271 - val_accuracy: 0.2383\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2364 - accuracy: 0.1696 - val_loss: 2.2358 - val_accuracy: 0.1567\n",
       "Epoch 48/300\n",
-      "2400/2400 [==============================] - 0s 175us/sample - loss: 2.1779 - accuracy: 0.2767 - val_loss: 2.2241 - val_accuracy: 0.2433\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2325 - accuracy: 0.1733 - val_loss: 2.2326 - val_accuracy: 0.1600\n",
       "Epoch 49/300\n",
-      "2400/2400 [==============================] - 0s 180us/sample - loss: 2.1746 - accuracy: 0.2829 - val_loss: 2.2211 - val_accuracy: 0.2467\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2286 - accuracy: 0.1750 - val_loss: 2.2294 - val_accuracy: 0.1600\n",
       "Epoch 50/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 2.1713 - accuracy: 0.2879 - val_loss: 2.2182 - val_accuracy: 0.2500\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2247 - accuracy: 0.1758 - val_loss: 2.2263 - val_accuracy: 0.1600\n",
       "Epoch 51/300\n",
-      "2400/2400 [==============================] - 0s 180us/sample - loss: 2.1681 - accuracy: 0.2933 - val_loss: 2.2153 - val_accuracy: 0.2550\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.2209 - accuracy: 0.1783 - val_loss: 2.2232 - val_accuracy: 0.1600\n",
       "Epoch 52/300\n",
-      "2400/2400 [==============================] - 0s 174us/sample - loss: 2.1649 - accuracy: 0.2988 - val_loss: 2.2124 - val_accuracy: 0.2583\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.2172 - accuracy: 0.1804 - val_loss: 2.2201 - val_accuracy: 0.1600\n",
       "Epoch 53/300\n",
-      "2400/2400 [==============================] - 0s 175us/sample - loss: 2.1618 - accuracy: 0.3033 - val_loss: 2.2096 - val_accuracy: 0.2633\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.2134 - accuracy: 0.1821 - val_loss: 2.2171 - val_accuracy: 0.1600\n",
       "Epoch 54/300\n",
-      "2400/2400 [==============================] - 0s 179us/sample - loss: 2.1587 - accuracy: 0.3096 - val_loss: 2.2068 - val_accuracy: 0.2650\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 2.2097 - accuracy: 0.1846 - val_loss: 2.2141 - val_accuracy: 0.1600\n",
       "Epoch 55/300\n",
-      "2400/2400 [==============================] - 0s 174us/sample - loss: 2.1556 - accuracy: 0.3154 - val_loss: 2.2040 - val_accuracy: 0.2733\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2061 - accuracy: 0.1875 - val_loss: 2.2112 - val_accuracy: 0.1617\n",
       "Epoch 56/300\n",
-      "2400/2400 [==============================] - 0s 179us/sample - loss: 2.1526 - accuracy: 0.3192 - val_loss: 2.2013 - val_accuracy: 0.2733\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.2025 - accuracy: 0.1908 - val_loss: 2.2083 - val_accuracy: 0.1617\n",
       "Epoch 57/300\n",
-      "2400/2400 [==============================] - 0s 187us/sample - loss: 2.1495 - accuracy: 0.3229 - val_loss: 2.1986 - val_accuracy: 0.2800\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1989 - accuracy: 0.1958 - val_loss: 2.2054 - val_accuracy: 0.1633\n",
       "Epoch 58/300\n",
-      "2400/2400 [==============================] - 0s 171us/sample - loss: 2.1465 - accuracy: 0.3262 - val_loss: 2.1959 - val_accuracy: 0.2867\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1954 - accuracy: 0.1992 - val_loss: 2.2025 - val_accuracy: 0.1633\n",
       "Epoch 59/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 2.1436 - accuracy: 0.3308 - val_loss: 2.1932 - val_accuracy: 0.2933\n",
+      "75/75 [==============================] - 1s 10ms/step - loss: 2.1918 - accuracy: 0.2013 - val_loss: 2.1997 - val_accuracy: 0.1650\n",
       "Epoch 60/300\n",
-      "2400/2400 [==============================] - 0s 172us/sample - loss: 2.1406 - accuracy: 0.3333 - val_loss: 2.1906 - val_accuracy: 0.2967\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1883 - accuracy: 0.2050 - val_loss: 2.1969 - val_accuracy: 0.1650\n",
       "Epoch 61/300\n",
-      "2400/2400 [==============================] - 0s 169us/sample - loss: 2.1377 - accuracy: 0.3388 - val_loss: 2.1879 - val_accuracy: 0.3033\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1848 - accuracy: 0.2067 - val_loss: 2.1941 - val_accuracy: 0.1683\n",
       "Epoch 62/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 2.1348 - accuracy: 0.3425 - val_loss: 2.1854 - val_accuracy: 0.3100\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 2.1814 - accuracy: 0.2083 - val_loss: 2.1914 - val_accuracy: 0.1750\n",
       "Epoch 63/300\n",
-      "2400/2400 [==============================] - 0s 184us/sample - loss: 2.1319 - accuracy: 0.3467 - val_loss: 2.1828 - val_accuracy: 0.3167\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1780 - accuracy: 0.2104 - val_loss: 2.1887 - val_accuracy: 0.1767\n",
       "Epoch 64/300\n",
-      "2400/2400 [==============================] - 0s 171us/sample - loss: 2.1290 - accuracy: 0.3517 - val_loss: 2.1802 - val_accuracy: 0.3217\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 2.1747 - accuracy: 0.2129 - val_loss: 2.1860 - val_accuracy: 0.1783\n",
       "Epoch 65/300\n",
-      "2400/2400 [==============================] - 0s 171us/sample - loss: 2.1262 - accuracy: 0.3554 - val_loss: 2.1777 - val_accuracy: 0.3233\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 2.1713 - accuracy: 0.2154 - val_loss: 2.1833 - val_accuracy: 0.1800\n",
       "Epoch 66/300\n",
-      "2400/2400 [==============================] - 0s 176us/sample - loss: 2.1233 - accuracy: 0.3579 - val_loss: 2.1752 - val_accuracy: 0.3300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.1680 - accuracy: 0.2179 - val_loss: 2.1807 - val_accuracy: 0.1817\n",
       "Epoch 67/300\n",
-      "2400/2400 [==============================] - 0s 167us/sample - loss: 2.1205 - accuracy: 0.3638 - val_loss: 2.1727 - val_accuracy: 0.3333\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1647 - accuracy: 0.2254 - val_loss: 2.1781 - val_accuracy: 0.1833\n",
       "Epoch 68/300\n",
-      "2400/2400 [==============================] - 0s 175us/sample - loss: 2.1178 - accuracy: 0.3667 - val_loss: 2.1702 - val_accuracy: 0.3367\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1615 - accuracy: 0.2296 - val_loss: 2.1755 - val_accuracy: 0.1883\n",
       "Epoch 69/300\n",
-      "2400/2400 [==============================] - 0s 170us/sample - loss: 2.1150 - accuracy: 0.3704 - val_loss: 2.1677 - val_accuracy: 0.3383\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1583 - accuracy: 0.2304 - val_loss: 2.1729 - val_accuracy: 0.1900\n",
       "Epoch 70/300\n",
-      "2400/2400 [==============================] - 0s 171us/sample - loss: 2.1122 - accuracy: 0.3733 - val_loss: 2.1653 - val_accuracy: 0.3433\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.1551 - accuracy: 0.2346 - val_loss: 2.1704 - val_accuracy: 0.1883\n",
       "Epoch 71/300\n",
-      "2400/2400 [==============================] - 0s 175us/sample - loss: 2.1095 - accuracy: 0.3767 - val_loss: 2.1629 - val_accuracy: 0.3450\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 2.1519 - accuracy: 0.2404 - val_loss: 2.1678 - val_accuracy: 0.1933\n",
       "Epoch 72/300\n",
-      "2400/2400 [==============================] - 0s 174us/sample - loss: 2.1068 - accuracy: 0.3800 - val_loss: 2.1605 - val_accuracy: 0.3467\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1488 - accuracy: 0.2454 - val_loss: 2.1653 - val_accuracy: 0.2017\n",
       "Epoch 73/300\n",
-      "2400/2400 [==============================] - 0s 174us/sample - loss: 2.1040 - accuracy: 0.3862 - val_loss: 2.1581 - val_accuracy: 0.3450\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 2.1456 - accuracy: 0.2492 - val_loss: 2.1628 - val_accuracy: 0.2017\n",
       "Epoch 74/300\n",
-      "2400/2400 [==============================] - 0s 181us/sample - loss: 2.1013 - accuracy: 0.3887 - val_loss: 2.1557 - val_accuracy: 0.3467\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 2.1425 - accuracy: 0.2562 - val_loss: 2.1603 - val_accuracy: 0.2050\n",
       "Epoch 75/300\n",
-      "2400/2400 [==============================] - 0s 179us/sample - loss: 2.0986 - accuracy: 0.3942 - val_loss: 2.1533 - val_accuracy: 0.3483\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1395 - accuracy: 0.2604 - val_loss: 2.1578 - val_accuracy: 0.2117\n",
       "Epoch 76/300\n",
-      "2400/2400 [==============================] - 0s 180us/sample - loss: 2.0960 - accuracy: 0.3979 - val_loss: 2.1510 - val_accuracy: 0.3500\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 2.1364 - accuracy: 0.2667 - val_loss: 2.1553 - val_accuracy: 0.2150\n",
       "Epoch 77/300\n",
-      "2400/2400 [==============================] - 0s 175us/sample - loss: 2.0933 - accuracy: 0.4004 - val_loss: 2.1486 - val_accuracy: 0.3500\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1334 - accuracy: 0.2708 - val_loss: 2.1529 - val_accuracy: 0.2217\n",
       "Epoch 78/300\n",
-      "2400/2400 [==============================] - 0s 180us/sample - loss: 2.0906 - accuracy: 0.4038 - val_loss: 2.1463 - val_accuracy: 0.3533\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1304 - accuracy: 0.2779 - val_loss: 2.1504 - val_accuracy: 0.2250\n",
       "Epoch 79/300\n",
-      "2400/2400 [==============================] - 0s 178us/sample - loss: 2.0880 - accuracy: 0.4087 - val_loss: 2.1440 - val_accuracy: 0.3550\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 2.1274 - accuracy: 0.2854 - val_loss: 2.1480 - val_accuracy: 0.2317\n",
       "Epoch 80/300\n",
-      "2400/2400 [==============================] - 0s 181us/sample - loss: 2.0854 - accuracy: 0.4137 - val_loss: 2.1417 - val_accuracy: 0.3600\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 2.1244 - accuracy: 0.2900 - val_loss: 2.1456 - val_accuracy: 0.2367\n",
       "Epoch 81/300\n",
-      "2400/2400 [==============================] - 0s 179us/sample - loss: 2.0828 - accuracy: 0.4167 - val_loss: 2.1394 - val_accuracy: 0.3600\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1215 - accuracy: 0.2950 - val_loss: 2.1432 - val_accuracy: 0.2433\n",
       "Epoch 82/300\n",
-      "2400/2400 [==============================] - 0s 174us/sample - loss: 2.0802 - accuracy: 0.4187 - val_loss: 2.1371 - val_accuracy: 0.3600\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.1186 - accuracy: 0.2971 - val_loss: 2.1408 - val_accuracy: 0.2467\n",
       "Epoch 83/300\n",
-      "2400/2400 [==============================] - 0s 171us/sample - loss: 2.0776 - accuracy: 0.4246 - val_loss: 2.1348 - val_accuracy: 0.3633\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1157 - accuracy: 0.3033 - val_loss: 2.1384 - val_accuracy: 0.2450\n",
       "Epoch 84/300\n",
-      "2400/2400 [==============================] - 0s 181us/sample - loss: 2.0750 - accuracy: 0.4267 - val_loss: 2.1326 - val_accuracy: 0.3667\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1128 - accuracy: 0.3129 - val_loss: 2.1361 - val_accuracy: 0.2533\n",
       "Epoch 85/300\n",
-      "2400/2400 [==============================] - 0s 175us/sample - loss: 2.0725 - accuracy: 0.4300 - val_loss: 2.1303 - val_accuracy: 0.3650\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 2.1099 - accuracy: 0.3171 - val_loss: 2.1338 - val_accuracy: 0.2583\n",
       "Epoch 86/300\n",
-      "2400/2400 [==============================] - 0s 171us/sample - loss: 2.0699 - accuracy: 0.4358 - val_loss: 2.1281 - val_accuracy: 0.3667\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.1071 - accuracy: 0.3225 - val_loss: 2.1314 - val_accuracy: 0.2617\n",
       "Epoch 87/300\n",
-      "2400/2400 [==============================] - 0s 188us/sample - loss: 2.0673 - accuracy: 0.4375 - val_loss: 2.1258 - val_accuracy: 0.3717\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1042 - accuracy: 0.3254 - val_loss: 2.1291 - val_accuracy: 0.2683\n",
       "Epoch 88/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 2.0648 - accuracy: 0.4408 - val_loss: 2.1236 - val_accuracy: 0.3750\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.1014 - accuracy: 0.3300 - val_loss: 2.1268 - val_accuracy: 0.2750\n",
       "Epoch 89/300\n",
-      "2400/2400 [==============================] - 0s 176us/sample - loss: 2.0622 - accuracy: 0.4450 - val_loss: 2.1214 - val_accuracy: 0.3750\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 2.0986 - accuracy: 0.3338 - val_loss: 2.1245 - val_accuracy: 0.2850\n",
       "Epoch 90/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 2.0597 - accuracy: 0.4483 - val_loss: 2.1192 - val_accuracy: 0.3800\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0958 - accuracy: 0.3408 - val_loss: 2.1222 - val_accuracy: 0.2850\n",
       "Epoch 91/300\n",
-      "2400/2400 [==============================] - 0s 178us/sample - loss: 2.0572 - accuracy: 0.4525 - val_loss: 2.1170 - val_accuracy: 0.3867\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.0930 - accuracy: 0.3471 - val_loss: 2.1199 - val_accuracy: 0.2950\n",
       "Epoch 92/300\n",
-      "2400/2400 [==============================] - 0s 165us/sample - loss: 2.0547 - accuracy: 0.4546 - val_loss: 2.1148 - val_accuracy: 0.3883\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.0902 - accuracy: 0.3504 - val_loss: 2.1176 - val_accuracy: 0.2983\n",
       "Epoch 93/300\n",
-      "2400/2400 [==============================] - 0s 167us/sample - loss: 2.0521 - accuracy: 0.4558 - val_loss: 2.1126 - val_accuracy: 0.3900\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 2.0875 - accuracy: 0.3562 - val_loss: 2.1154 - val_accuracy: 0.3083\n",
       "Epoch 94/300\n",
-      "2400/2400 [==============================] - 0s 173us/sample - loss: 2.0496 - accuracy: 0.4571 - val_loss: 2.1104 - val_accuracy: 0.3933\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0847 - accuracy: 0.3617 - val_loss: 2.1131 - val_accuracy: 0.3083\n",
       "Epoch 95/300\n",
-      "2400/2400 [==============================] - 0s 157us/sample - loss: 2.0471 - accuracy: 0.4596 - val_loss: 2.1083 - val_accuracy: 0.3933\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0820 - accuracy: 0.3654 - val_loss: 2.1108 - val_accuracy: 0.3200\n",
       "Epoch 96/300\n",
-      "2400/2400 [==============================] - 0s 167us/sample - loss: 2.0446 - accuracy: 0.4667 - val_loss: 2.1061 - val_accuracy: 0.3967\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0792 - accuracy: 0.3692 - val_loss: 2.1086 - val_accuracy: 0.3233\n",
       "Epoch 97/300\n",
-      "2400/2400 [==============================] - 0s 175us/sample - loss: 2.0422 - accuracy: 0.4683 - val_loss: 2.1039 - val_accuracy: 0.3967\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 2.0765 - accuracy: 0.3742 - val_loss: 2.1064 - val_accuracy: 0.3283\n",
       "Epoch 98/300\n",
-      "2400/2400 [==============================] - 0s 173us/sample - loss: 2.0397 - accuracy: 0.4725 - val_loss: 2.1018 - val_accuracy: 0.3967\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.0738 - accuracy: 0.3783 - val_loss: 2.1041 - val_accuracy: 0.3300\n",
       "Epoch 99/300\n",
-      "2400/2400 [==============================] - 0s 176us/sample - loss: 2.0372 - accuracy: 0.4771 - val_loss: 2.0996 - val_accuracy: 0.4017\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0711 - accuracy: 0.3833 - val_loss: 2.1019 - val_accuracy: 0.3333\n",
       "Epoch 100/300\n",
-      "2400/2400 [==============================] - 0s 168us/sample - loss: 2.0348 - accuracy: 0.4783 - val_loss: 2.0975 - val_accuracy: 0.4033\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 2.0684 - accuracy: 0.3887 - val_loss: 2.0998 - val_accuracy: 0.3433\n",
       "Epoch 101/300\n",
-      "2400/2400 [==============================] - 0s 168us/sample - loss: 2.0323 - accuracy: 0.4837 - val_loss: 2.0954 - val_accuracy: 0.4067\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0657 - accuracy: 0.3946 - val_loss: 2.0976 - val_accuracy: 0.3483\n",
       "Epoch 102/300\n",
-      "2400/2400 [==============================] - 0s 174us/sample - loss: 2.0299 - accuracy: 0.4854 - val_loss: 2.0932 - val_accuracy: 0.4067\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0630 - accuracy: 0.4013 - val_loss: 2.0954 - val_accuracy: 0.3517\n",
       "Epoch 103/300\n",
-      "2400/2400 [==============================] - 0s 175us/sample - loss: 2.0275 - accuracy: 0.4879 - val_loss: 2.0911 - val_accuracy: 0.4083\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.0604 - accuracy: 0.4054 - val_loss: 2.0932 - val_accuracy: 0.3567\n",
       "Epoch 104/300\n",
-      "2400/2400 [==============================] - 0s 169us/sample - loss: 2.0250 - accuracy: 0.4904 - val_loss: 2.0890 - val_accuracy: 0.4083\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0577 - accuracy: 0.4133 - val_loss: 2.0910 - val_accuracy: 0.3633\n",
       "Epoch 105/300\n",
-      "2400/2400 [==============================] - 0s 162us/sample - loss: 2.0226 - accuracy: 0.4942 - val_loss: 2.0869 - val_accuracy: 0.4100\n",
+      "75/75 [==============================] - 1s 10ms/step - loss: 2.0551 - accuracy: 0.4179 - val_loss: 2.0888 - val_accuracy: 0.3617\n",
       "Epoch 106/300\n",
-      "2400/2400 [==============================] - 0s 179us/sample - loss: 2.0202 - accuracy: 0.4950 - val_loss: 2.0849 - val_accuracy: 0.4100\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0524 - accuracy: 0.4212 - val_loss: 2.0866 - val_accuracy: 0.3667\n",
       "Epoch 107/300\n",
-      "2400/2400 [==============================] - 0s 173us/sample - loss: 2.0178 - accuracy: 0.4967 - val_loss: 2.0828 - val_accuracy: 0.4117\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 2.0497 - accuracy: 0.4283 - val_loss: 2.0844 - val_accuracy: 0.3700\n",
       "Epoch 108/300\n",
-      "2400/2400 [==============================] - 0s 171us/sample - loss: 2.0155 - accuracy: 0.5004 - val_loss: 2.0807 - val_accuracy: 0.4117\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 2.0471 - accuracy: 0.4346 - val_loss: 2.0822 - val_accuracy: 0.3717\n",
       "Epoch 109/300\n",
-      "2400/2400 [==============================] - 0s 168us/sample - loss: 2.0131 - accuracy: 0.5033 - val_loss: 2.0787 - val_accuracy: 0.4133\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0445 - accuracy: 0.4379 - val_loss: 2.0801 - val_accuracy: 0.3767\n",
       "Epoch 110/300\n",
-      "2400/2400 [==============================] - 0s 160us/sample - loss: 2.0107 - accuracy: 0.5058 - val_loss: 2.0766 - val_accuracy: 0.4150\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0418 - accuracy: 0.4446 - val_loss: 2.0779 - val_accuracy: 0.3817\n",
       "Epoch 111/300\n",
-      "2400/2400 [==============================] - 0s 165us/sample - loss: 2.0084 - accuracy: 0.5075 - val_loss: 2.0746 - val_accuracy: 0.4183\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0392 - accuracy: 0.4504 - val_loss: 2.0757 - val_accuracy: 0.3833\n",
       "Epoch 112/300\n",
-      "2400/2400 [==============================] - 0s 150us/sample - loss: 2.0060 - accuracy: 0.5108 - val_loss: 2.0725 - val_accuracy: 0.4233\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.0366 - accuracy: 0.4592 - val_loss: 2.0735 - val_accuracy: 0.3933\n",
       "Epoch 113/300\n",
-      "2400/2400 [==============================] - 0s 168us/sample - loss: 2.0037 - accuracy: 0.5129 - val_loss: 2.0705 - val_accuracy: 0.4250\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0340 - accuracy: 0.4663 - val_loss: 2.0714 - val_accuracy: 0.3983\n",
       "Epoch 114/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 2.0013 - accuracy: 0.5146 - val_loss: 2.0684 - val_accuracy: 0.4267\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0314 - accuracy: 0.4717 - val_loss: 2.0692 - val_accuracy: 0.4050\n",
       "Epoch 115/300\n",
-      "2400/2400 [==============================] - 0s 189us/sample - loss: 1.9990 - accuracy: 0.5171 - val_loss: 2.0664 - val_accuracy: 0.4333\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0289 - accuracy: 0.4758 - val_loss: 2.0670 - val_accuracy: 0.4050\n",
       "Epoch 116/300\n",
-      "2400/2400 [==============================] - 0s 181us/sample - loss: 1.9967 - accuracy: 0.5188 - val_loss: 2.0644 - val_accuracy: 0.4333\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 2.0263 - accuracy: 0.4812 - val_loss: 2.0649 - val_accuracy: 0.4067\n",
       "Epoch 117/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 1.9944 - accuracy: 0.5213 - val_loss: 2.0624 - val_accuracy: 0.4367\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0237 - accuracy: 0.4879 - val_loss: 2.0627 - val_accuracy: 0.4100\n",
       "Epoch 118/300\n",
-      "2400/2400 [==============================] - 0s 163us/sample - loss: 1.9921 - accuracy: 0.5229 - val_loss: 2.0604 - val_accuracy: 0.4383\n",
+      "75/75 [==============================] - 1s 10ms/step - loss: 2.0212 - accuracy: 0.4946 - val_loss: 2.0605 - val_accuracy: 0.4183\n",
       "Epoch 119/300\n",
-      "2400/2400 [==============================] - 0s 166us/sample - loss: 1.9898 - accuracy: 0.5267 - val_loss: 2.0583 - val_accuracy: 0.4417\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.0186 - accuracy: 0.5021 - val_loss: 2.0584 - val_accuracy: 0.4217\n",
       "Epoch 120/300\n",
-      "2400/2400 [==============================] - 0s 173us/sample - loss: 1.9874 - accuracy: 0.5279 - val_loss: 2.0563 - val_accuracy: 0.4417\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0161 - accuracy: 0.5050 - val_loss: 2.0562 - val_accuracy: 0.4250\n",
       "Epoch 121/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 1.9851 - accuracy: 0.5308 - val_loss: 2.0543 - val_accuracy: 0.4433\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0135 - accuracy: 0.5092 - val_loss: 2.0541 - val_accuracy: 0.4283\n",
       "Epoch 122/300\n",
-      "2400/2400 [==============================] - 0s 176us/sample - loss: 1.9829 - accuracy: 0.5333 - val_loss: 2.0523 - val_accuracy: 0.4433\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0110 - accuracy: 0.5117 - val_loss: 2.0519 - val_accuracy: 0.4317\n",
       "Epoch 123/300\n",
-      "2400/2400 [==============================] - 0s 174us/sample - loss: 1.9806 - accuracy: 0.5362 - val_loss: 2.0503 - val_accuracy: 0.4450\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0085 - accuracy: 0.5167 - val_loss: 2.0498 - val_accuracy: 0.4367\n",
       "Epoch 124/300\n",
-      "2400/2400 [==============================] - 0s 190us/sample - loss: 1.9783 - accuracy: 0.5375 - val_loss: 2.0483 - val_accuracy: 0.4450\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 2.0060 - accuracy: 0.5179 - val_loss: 2.0477 - val_accuracy: 0.4383\n",
       "Epoch 125/300\n",
-      "2400/2400 [==============================] - 0s 183us/sample - loss: 1.9760 - accuracy: 0.5408 - val_loss: 2.0463 - val_accuracy: 0.4450\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 2.0035 - accuracy: 0.5225 - val_loss: 2.0456 - val_accuracy: 0.4433\n",
       "Epoch 126/300\n",
-      "2400/2400 [==============================] - 0s 171us/sample - loss: 1.9738 - accuracy: 0.5437 - val_loss: 2.0443 - val_accuracy: 0.4450\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 2.0010 - accuracy: 0.5254 - val_loss: 2.0434 - val_accuracy: 0.4467\n",
       "Epoch 127/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 1.9715 - accuracy: 0.5471 - val_loss: 2.0423 - val_accuracy: 0.4467\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.9985 - accuracy: 0.5279 - val_loss: 2.0413 - val_accuracy: 0.4533\n",
       "Epoch 128/300\n",
-      "2400/2400 [==============================] - 0s 192us/sample - loss: 1.9692 - accuracy: 0.5487 - val_loss: 2.0403 - val_accuracy: 0.4483\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9960 - accuracy: 0.5312 - val_loss: 2.0392 - val_accuracy: 0.4583\n",
       "Epoch 129/300\n",
-      "2400/2400 [==============================] - 0s 184us/sample - loss: 1.9670 - accuracy: 0.5508 - val_loss: 2.0383 - val_accuracy: 0.4483\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.9935 - accuracy: 0.5375 - val_loss: 2.0371 - val_accuracy: 0.4617\n",
       "Epoch 130/300\n",
-      "2400/2400 [==============================] - 0s 176us/sample - loss: 1.9647 - accuracy: 0.5525 - val_loss: 2.0363 - val_accuracy: 0.4500\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9911 - accuracy: 0.5400 - val_loss: 2.0351 - val_accuracy: 0.4617\n",
       "Epoch 131/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 1.9625 - accuracy: 0.5542 - val_loss: 2.0344 - val_accuracy: 0.4517\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.9886 - accuracy: 0.5450 - val_loss: 2.0330 - val_accuracy: 0.4617\n",
       "Epoch 132/300\n",
-      "2400/2400 [==============================] - 0s 175us/sample - loss: 1.9602 - accuracy: 0.5579 - val_loss: 2.0324 - val_accuracy: 0.4550\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.9862 - accuracy: 0.5483 - val_loss: 2.0309 - val_accuracy: 0.4650\n",
       "Epoch 133/300\n",
-      "2400/2400 [==============================] - 0s 173us/sample - loss: 1.9580 - accuracy: 0.5596 - val_loss: 2.0304 - val_accuracy: 0.4583\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9837 - accuracy: 0.5487 - val_loss: 2.0288 - val_accuracy: 0.4683\n",
       "Epoch 134/300\n",
-      "2400/2400 [==============================] - 0s 149us/sample - loss: 1.9558 - accuracy: 0.5621 - val_loss: 2.0285 - val_accuracy: 0.4583\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.9813 - accuracy: 0.5558 - val_loss: 2.0268 - val_accuracy: 0.4750\n",
       "Epoch 135/300\n",
-      "2400/2400 [==============================] - 0s 178us/sample - loss: 1.9535 - accuracy: 0.5650 - val_loss: 2.0265 - val_accuracy: 0.4600\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.9789 - accuracy: 0.5596 - val_loss: 2.0247 - val_accuracy: 0.4783\n",
       "Epoch 136/300\n",
-      "2400/2400 [==============================] - 0s 187us/sample - loss: 1.9513 - accuracy: 0.5675 - val_loss: 2.0246 - val_accuracy: 0.4617\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9765 - accuracy: 0.5629 - val_loss: 2.0227 - val_accuracy: 0.4800\n",
       "Epoch 137/300\n",
-      "2400/2400 [==============================] - 0s 171us/sample - loss: 1.9491 - accuracy: 0.5704 - val_loss: 2.0226 - val_accuracy: 0.4617\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9740 - accuracy: 0.5679 - val_loss: 2.0207 - val_accuracy: 0.4833\n",
       "Epoch 138/300\n",
-      "2400/2400 [==============================] - 0s 164us/sample - loss: 1.9469 - accuracy: 0.5721 - val_loss: 2.0207 - val_accuracy: 0.4633\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.9716 - accuracy: 0.5700 - val_loss: 2.0186 - val_accuracy: 0.4850\n",
       "Epoch 139/300\n",
-      "2400/2400 [==============================] - 0s 188us/sample - loss: 1.9447 - accuracy: 0.5721 - val_loss: 2.0188 - val_accuracy: 0.4650\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9692 - accuracy: 0.5742 - val_loss: 2.0166 - val_accuracy: 0.4867\n",
       "Epoch 140/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 1.9425 - accuracy: 0.5721 - val_loss: 2.0168 - val_accuracy: 0.4650\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9668 - accuracy: 0.5775 - val_loss: 2.0146 - val_accuracy: 0.4850\n",
       "Epoch 141/300\n",
-      "2400/2400 [==============================] - 0s 163us/sample - loss: 1.9403 - accuracy: 0.5746 - val_loss: 2.0149 - val_accuracy: 0.4683\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9644 - accuracy: 0.5796 - val_loss: 2.0126 - val_accuracy: 0.4850\n",
       "Epoch 142/300\n",
-      "2400/2400 [==============================] - 0s 174us/sample - loss: 1.9381 - accuracy: 0.5754 - val_loss: 2.0130 - val_accuracy: 0.4700\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 1.9620 - accuracy: 0.5825 - val_loss: 2.0106 - val_accuracy: 0.4883\n",
       "Epoch 143/300\n",
-      "2400/2400 [==============================] - 0s 173us/sample - loss: 1.9359 - accuracy: 0.5771 - val_loss: 2.0111 - val_accuracy: 0.4700\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9596 - accuracy: 0.5854 - val_loss: 2.0086 - val_accuracy: 0.4917\n",
       "Epoch 144/300\n",
-      "2400/2400 [==============================] - 0s 172us/sample - loss: 1.9337 - accuracy: 0.5792 - val_loss: 2.0092 - val_accuracy: 0.4700\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.9572 - accuracy: 0.5883 - val_loss: 2.0066 - val_accuracy: 0.4950\n",
       "Epoch 145/300\n",
-      "2400/2400 [==============================] - 0s 174us/sample - loss: 1.9315 - accuracy: 0.5817 - val_loss: 2.0073 - val_accuracy: 0.4717\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.9548 - accuracy: 0.5929 - val_loss: 2.0046 - val_accuracy: 0.4967\n",
       "Epoch 146/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 1.9294 - accuracy: 0.5833 - val_loss: 2.0054 - val_accuracy: 0.4717\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9524 - accuracy: 0.5979 - val_loss: 2.0026 - val_accuracy: 0.4983\n",
       "Epoch 147/300\n",
-      "2400/2400 [==============================] - 0s 187us/sample - loss: 1.9272 - accuracy: 0.5854 - val_loss: 2.0035 - val_accuracy: 0.4717\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.9500 - accuracy: 0.5996 - val_loss: 2.0006 - val_accuracy: 0.4983\n",
       "Epoch 148/300\n",
-      "2400/2400 [==============================] - 0s 169us/sample - loss: 1.9250 - accuracy: 0.5875 - val_loss: 2.0017 - val_accuracy: 0.4733\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.9477 - accuracy: 0.6012 - val_loss: 1.9986 - val_accuracy: 0.5000\n",
       "Epoch 149/300\n",
-      "2400/2400 [==============================] - 0s 153us/sample - loss: 1.9229 - accuracy: 0.5896 - val_loss: 1.9998 - val_accuracy: 0.4733\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9453 - accuracy: 0.6037 - val_loss: 1.9966 - val_accuracy: 0.5033\n",
       "Epoch 150/300\n",
-      "2400/2400 [==============================] - 0s 147us/sample - loss: 1.9207 - accuracy: 0.5900 - val_loss: 1.9979 - val_accuracy: 0.4750\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9429 - accuracy: 0.6087 - val_loss: 1.9946 - val_accuracy: 0.5067\n",
       "Epoch 151/300\n",
-      "2400/2400 [==============================] - 0s 165us/sample - loss: 1.9186 - accuracy: 0.5929 - val_loss: 1.9960 - val_accuracy: 0.4750\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.9406 - accuracy: 0.6108 - val_loss: 1.9926 - val_accuracy: 0.5100\n",
       "Epoch 152/300\n",
-      "2400/2400 [==============================] - 0s 165us/sample - loss: 1.9164 - accuracy: 0.5929 - val_loss: 1.9941 - val_accuracy: 0.4750\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.9382 - accuracy: 0.6117 - val_loss: 1.9906 - val_accuracy: 0.5133\n",
       "Epoch 153/300\n",
-      "2400/2400 [==============================] - 0s 183us/sample - loss: 1.9143 - accuracy: 0.5946 - val_loss: 1.9923 - val_accuracy: 0.4767\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9358 - accuracy: 0.6167 - val_loss: 1.9886 - val_accuracy: 0.5150\n",
       "Epoch 154/300\n",
-      "2400/2400 [==============================] - 0s 178us/sample - loss: 1.9121 - accuracy: 0.5971 - val_loss: 1.9904 - val_accuracy: 0.4783\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.9335 - accuracy: 0.6167 - val_loss: 1.9867 - val_accuracy: 0.5183\n",
       "Epoch 155/300\n",
-      "2400/2400 [==============================] - 0s 173us/sample - loss: 1.9100 - accuracy: 0.5975 - val_loss: 1.9885 - val_accuracy: 0.4800\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.9311 - accuracy: 0.6196 - val_loss: 1.9847 - val_accuracy: 0.5200\n",
       "Epoch 156/300\n",
-      "2400/2400 [==============================] - 0s 148us/sample - loss: 1.9079 - accuracy: 0.5996 - val_loss: 1.9866 - val_accuracy: 0.4817\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9288 - accuracy: 0.6242 - val_loss: 1.9827 - val_accuracy: 0.5217\n",
       "Epoch 157/300\n",
-      "2400/2400 [==============================] - 0s 176us/sample - loss: 1.9058 - accuracy: 0.6000 - val_loss: 1.9848 - val_accuracy: 0.4833\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.9264 - accuracy: 0.6250 - val_loss: 1.9807 - val_accuracy: 0.5250\n",
       "Epoch 158/300\n",
-      "2400/2400 [==============================] - 0s 179us/sample - loss: 1.9036 - accuracy: 0.6004 - val_loss: 1.9829 - val_accuracy: 0.4817\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.9241 - accuracy: 0.6275 - val_loss: 1.9787 - val_accuracy: 0.5250\n",
       "Epoch 159/300\n",
-      "2400/2400 [==============================] - 0s 164us/sample - loss: 1.9015 - accuracy: 0.6008 - val_loss: 1.9811 - val_accuracy: 0.4817\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9217 - accuracy: 0.6304 - val_loss: 1.9767 - val_accuracy: 0.5300\n",
       "Epoch 160/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 1.8994 - accuracy: 0.6033 - val_loss: 1.9792 - val_accuracy: 0.4833\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9194 - accuracy: 0.6338 - val_loss: 1.9748 - val_accuracy: 0.5300\n",
       "Epoch 161/300\n",
-      "2400/2400 [==============================] - 0s 169us/sample - loss: 1.8973 - accuracy: 0.6054 - val_loss: 1.9774 - val_accuracy: 0.4850\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9171 - accuracy: 0.6363 - val_loss: 1.9728 - val_accuracy: 0.5317\n",
       "Epoch 162/300\n",
-      "2400/2400 [==============================] - 0s 167us/sample - loss: 1.8952 - accuracy: 0.6079 - val_loss: 1.9755 - val_accuracy: 0.4850\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.9147 - accuracy: 0.6371 - val_loss: 1.9708 - val_accuracy: 0.5350\n",
       "Epoch 163/300\n",
-      "2400/2400 [==============================] - 0s 178us/sample - loss: 1.8931 - accuracy: 0.6096 - val_loss: 1.9737 - val_accuracy: 0.4900\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9124 - accuracy: 0.6400 - val_loss: 1.9688 - val_accuracy: 0.5350\n",
       "Epoch 164/300\n",
-      "2400/2400 [==============================] - 0s 169us/sample - loss: 1.8910 - accuracy: 0.6112 - val_loss: 1.9718 - val_accuracy: 0.4900\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.9101 - accuracy: 0.6388 - val_loss: 1.9668 - val_accuracy: 0.5350\n",
       "Epoch 165/300\n",
-      "2400/2400 [==============================] - 0s 168us/sample - loss: 1.8889 - accuracy: 0.6121 - val_loss: 1.9700 - val_accuracy: 0.4917\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.9077 - accuracy: 0.6413 - val_loss: 1.9648 - val_accuracy: 0.5367\n",
       "Epoch 166/300\n",
-      "2400/2400 [==============================] - 0s 161us/sample - loss: 1.8868 - accuracy: 0.6125 - val_loss: 1.9681 - val_accuracy: 0.4917\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9054 - accuracy: 0.6446 - val_loss: 1.9629 - val_accuracy: 0.5367\n",
       "Epoch 167/300\n",
-      "2400/2400 [==============================] - 0s 178us/sample - loss: 1.8847 - accuracy: 0.6142 - val_loss: 1.9663 - val_accuracy: 0.4933\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.9031 - accuracy: 0.6450 - val_loss: 1.9609 - val_accuracy: 0.5367\n",
       "Epoch 168/300\n",
-      "2400/2400 [==============================] - 0s 175us/sample - loss: 1.8826 - accuracy: 0.6158 - val_loss: 1.9644 - val_accuracy: 0.4950\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.9008 - accuracy: 0.6467 - val_loss: 1.9589 - val_accuracy: 0.5383\n",
       "Epoch 169/300\n",
-      "2400/2400 [==============================] - 0s 185us/sample - loss: 1.8805 - accuracy: 0.6167 - val_loss: 1.9626 - val_accuracy: 0.4967\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8985 - accuracy: 0.6488 - val_loss: 1.9570 - val_accuracy: 0.5467\n",
       "Epoch 170/300\n",
-      "2400/2400 [==============================] - 0s 183us/sample - loss: 1.8784 - accuracy: 0.6171 - val_loss: 1.9607 - val_accuracy: 0.4967\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8962 - accuracy: 0.6525 - val_loss: 1.9550 - val_accuracy: 0.5483\n",
       "Epoch 171/300\n",
-      "2400/2400 [==============================] - 0s 176us/sample - loss: 1.8763 - accuracy: 0.6183 - val_loss: 1.9589 - val_accuracy: 0.4967\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.8939 - accuracy: 0.6538 - val_loss: 1.9531 - val_accuracy: 0.5533\n",
       "Epoch 172/300\n",
-      "2400/2400 [==============================] - 0s 163us/sample - loss: 1.8742 - accuracy: 0.6192 - val_loss: 1.9570 - val_accuracy: 0.4983\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8916 - accuracy: 0.6554 - val_loss: 1.9511 - val_accuracy: 0.5567\n",
       "Epoch 173/300\n",
-      "2400/2400 [==============================] - 0s 167us/sample - loss: 1.8722 - accuracy: 0.6192 - val_loss: 1.9552 - val_accuracy: 0.5000\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.8893 - accuracy: 0.6562 - val_loss: 1.9492 - val_accuracy: 0.5583\n",
       "Epoch 174/300\n",
-      "2400/2400 [==============================] - 0s 178us/sample - loss: 1.8701 - accuracy: 0.6204 - val_loss: 1.9534 - val_accuracy: 0.5000\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8870 - accuracy: 0.6600 - val_loss: 1.9473 - val_accuracy: 0.5600\n",
       "Epoch 175/300\n",
-      "2400/2400 [==============================] - 0s 178us/sample - loss: 1.8680 - accuracy: 0.6221 - val_loss: 1.9516 - val_accuracy: 0.5000\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8847 - accuracy: 0.6621 - val_loss: 1.9453 - val_accuracy: 0.5617\n",
       "Epoch 176/300\n",
-      "2400/2400 [==============================] - 0s 141us/sample - loss: 1.8659 - accuracy: 0.6246 - val_loss: 1.9497 - val_accuracy: 0.5000\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8824 - accuracy: 0.6658 - val_loss: 1.9434 - val_accuracy: 0.5633\n",
       "Epoch 177/300\n",
-      "2400/2400 [==============================] - 0s 172us/sample - loss: 1.8639 - accuracy: 0.6254 - val_loss: 1.9479 - val_accuracy: 0.5017\n",
+      "75/75 [==============================] - 1s 10ms/step - loss: 1.8802 - accuracy: 0.6679 - val_loss: 1.9415 - val_accuracy: 0.5667\n",
       "Epoch 178/300\n",
-      "2400/2400 [==============================] - 0s 183us/sample - loss: 1.8618 - accuracy: 0.6275 - val_loss: 1.9461 - val_accuracy: 0.5033\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.8779 - accuracy: 0.6692 - val_loss: 1.9396 - val_accuracy: 0.5683\n",
       "Epoch 179/300\n",
-      "2400/2400 [==============================] - 0s 170us/sample - loss: 1.8598 - accuracy: 0.6275 - val_loss: 1.9443 - val_accuracy: 0.5067\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8756 - accuracy: 0.6733 - val_loss: 1.9377 - val_accuracy: 0.5700\n",
       "Epoch 180/300\n",
-      "2400/2400 [==============================] - 0s 181us/sample - loss: 1.8577 - accuracy: 0.6283 - val_loss: 1.9425 - val_accuracy: 0.5067\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 1.8734 - accuracy: 0.6750 - val_loss: 1.9358 - val_accuracy: 0.5700\n",
       "Epoch 181/300\n",
-      "2400/2400 [==============================] - 0s 177us/sample - loss: 1.8557 - accuracy: 0.6292 - val_loss: 1.9407 - val_accuracy: 0.5083\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8711 - accuracy: 0.6775 - val_loss: 1.9339 - val_accuracy: 0.5733\n",
       "Epoch 182/300\n",
-      "2400/2400 [==============================] - 0s 186us/sample - loss: 1.8536 - accuracy: 0.6313 - val_loss: 1.9389 - val_accuracy: 0.5067\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.8688 - accuracy: 0.6792 - val_loss: 1.9320 - val_accuracy: 0.5733\n",
       "Epoch 183/300\n",
-      "2400/2400 [==============================] - 0s 174us/sample - loss: 1.8516 - accuracy: 0.6321 - val_loss: 1.9371 - val_accuracy: 0.5083\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.8666 - accuracy: 0.6812 - val_loss: 1.9301 - val_accuracy: 0.5750\n",
       "Epoch 184/300\n",
-      "2400/2400 [==============================] - 0s 170us/sample - loss: 1.8495 - accuracy: 0.6338 - val_loss: 1.9353 - val_accuracy: 0.5100\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.8643 - accuracy: 0.6817 - val_loss: 1.9282 - val_accuracy: 0.5750\n",
       "Epoch 185/300\n",
-      "2400/2400 [==============================] - 0s 183us/sample - loss: 1.8475 - accuracy: 0.6346 - val_loss: 1.9335 - val_accuracy: 0.5100\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8620 - accuracy: 0.6825 - val_loss: 1.9263 - val_accuracy: 0.5750\n",
       "Epoch 186/300\n",
-      "2400/2400 [==============================] - 0s 185us/sample - loss: 1.8454 - accuracy: 0.6350 - val_loss: 1.9316 - val_accuracy: 0.5117\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8598 - accuracy: 0.6833 - val_loss: 1.9245 - val_accuracy: 0.5733\n",
       "Epoch 187/300\n",
-      "2400/2400 [==============================] - 0s 183us/sample - loss: 1.8434 - accuracy: 0.6358 - val_loss: 1.9298 - val_accuracy: 0.5133\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8575 - accuracy: 0.6850 - val_loss: 1.9226 - val_accuracy: 0.5733\n",
       "Epoch 188/300\n",
-      "2400/2400 [==============================] - 0s 167us/sample - loss: 1.8414 - accuracy: 0.6363 - val_loss: 1.9280 - val_accuracy: 0.5150\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 1.8553 - accuracy: 0.6867 - val_loss: 1.9207 - val_accuracy: 0.5750\n",
       "Epoch 189/300\n",
-      "2400/2400 [==============================] - 0s 170us/sample - loss: 1.8393 - accuracy: 0.6354 - val_loss: 1.9263 - val_accuracy: 0.5167\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8531 - accuracy: 0.6858 - val_loss: 1.9188 - val_accuracy: 0.5767\n",
       "Epoch 190/300\n",
-      "2400/2400 [==============================] - 0s 165us/sample - loss: 1.8373 - accuracy: 0.6375 - val_loss: 1.9245 - val_accuracy: 0.5167\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.8509 - accuracy: 0.6896 - val_loss: 1.9170 - val_accuracy: 0.5783\n",
       "Epoch 191/300\n",
-      "2400/2400 [==============================] - 0s 162us/sample - loss: 1.8353 - accuracy: 0.6400 - val_loss: 1.9227 - val_accuracy: 0.5183\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8486 - accuracy: 0.6917 - val_loss: 1.9151 - val_accuracy: 0.5783\n",
       "Epoch 192/300\n",
-      "2400/2400 [==============================] - 0s 172us/sample - loss: 1.8333 - accuracy: 0.6404 - val_loss: 1.9209 - val_accuracy: 0.5183\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8464 - accuracy: 0.6938 - val_loss: 1.9132 - val_accuracy: 0.5783\n",
       "Epoch 193/300\n",
-      "2400/2400 [==============================] - 0s 187us/sample - loss: 1.8313 - accuracy: 0.6404 - val_loss: 1.9191 - val_accuracy: 0.5217\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8442 - accuracy: 0.6958 - val_loss: 1.9114 - val_accuracy: 0.5800\n",
       "Epoch 194/300\n",
-      "2400/2400 [==============================] - 0s 199us/sample - loss: 1.8293 - accuracy: 0.6404 - val_loss: 1.9174 - val_accuracy: 0.5250\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.8420 - accuracy: 0.6971 - val_loss: 1.9095 - val_accuracy: 0.5833\n",
       "Epoch 195/300\n",
-      "2400/2400 [==============================] - 0s 164us/sample - loss: 1.8273 - accuracy: 0.6404 - val_loss: 1.9156 - val_accuracy: 0.5267\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8398 - accuracy: 0.6988 - val_loss: 1.9077 - val_accuracy: 0.5850\n",
       "Epoch 196/300\n",
-      "2112/2400 [=========================>....] - ETA: 0s - loss: 1.8267 - accuracy: 0.6430"
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.8376 - accuracy: 0.6996 - val_loss: 1.9058 - val_accuracy: 0.5867\n",
+      "Epoch 197/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8354 - accuracy: 0.7021 - val_loss: 1.9040 - val_accuracy: 0.5867\n",
+      "Epoch 198/300\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.8332 - accuracy: 0.7025 - val_loss: 1.9021 - val_accuracy: 0.5883\n",
+      "Epoch 199/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.8310 - accuracy: 0.7042 - val_loss: 1.9003 - val_accuracy: 0.5883\n",
+      "Epoch 200/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8288 - accuracy: 0.7042 - val_loss: 1.8984 - val_accuracy: 0.5883\n",
+      "Epoch 201/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8266 - accuracy: 0.7063 - val_loss: 1.8966 - val_accuracy: 0.5900\n",
+      "Epoch 202/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.8244 - accuracy: 0.7079 - val_loss: 1.8947 - val_accuracy: 0.5917\n",
+      "Epoch 203/300\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.8222 - accuracy: 0.7075 - val_loss: 1.8929 - val_accuracy: 0.5917\n",
+      "Epoch 204/300\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 1.8200 - accuracy: 0.7088 - val_loss: 1.8910 - val_accuracy: 0.5917\n",
+      "Epoch 205/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8179 - accuracy: 0.7100 - val_loss: 1.8892 - val_accuracy: 0.5933\n",
+      "Epoch 206/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8157 - accuracy: 0.7100 - val_loss: 1.8873 - val_accuracy: 0.5933\n",
+      "Epoch 207/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8135 - accuracy: 0.7117 - val_loss: 1.8855 - val_accuracy: 0.5933\n",
+      "Epoch 208/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8113 - accuracy: 0.7117 - val_loss: 1.8836 - val_accuracy: 0.5967\n",
+      "Epoch 209/300\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.8092 - accuracy: 0.7129 - val_loss: 1.8818 - val_accuracy: 0.5967\n",
+      "Epoch 210/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.8070 - accuracy: 0.7146 - val_loss: 1.8800 - val_accuracy: 0.5967\n",
+      "Epoch 211/300\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.8048 - accuracy: 0.7154 - val_loss: 1.8781 - val_accuracy: 0.5967\n",
+      "Epoch 212/300\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.8027 - accuracy: 0.7175 - val_loss: 1.8763 - val_accuracy: 0.6017\n",
+      "Epoch 213/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.8006 - accuracy: 0.7171 - val_loss: 1.8745 - val_accuracy: 0.6017\n",
+      "Epoch 214/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.7984 - accuracy: 0.7183 - val_loss: 1.8727 - val_accuracy: 0.6033\n",
+      "Epoch 215/300\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.7963 - accuracy: 0.7188 - val_loss: 1.8708 - val_accuracy: 0.6017\n",
+      "Epoch 216/300\n",
+      "75/75 [==============================] - 1s 10ms/step - loss: 1.7942 - accuracy: 0.7200 - val_loss: 1.8690 - val_accuracy: 0.6017\n",
+      "Epoch 217/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7920 - accuracy: 0.7204 - val_loss: 1.8672 - val_accuracy: 0.6050\n",
+      "Epoch 218/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7899 - accuracy: 0.7208 - val_loss: 1.8654 - val_accuracy: 0.6050\n",
+      "Epoch 219/300\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.7878 - accuracy: 0.7212 - val_loss: 1.8636 - val_accuracy: 0.6083\n",
+      "Epoch 220/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7857 - accuracy: 0.7229 - val_loss: 1.8618 - val_accuracy: 0.6100\n",
+      "Epoch 221/300\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.7835 - accuracy: 0.7246 - val_loss: 1.8600 - val_accuracy: 0.6100\n",
+      "Epoch 222/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.7814 - accuracy: 0.7254 - val_loss: 1.8581 - val_accuracy: 0.6100\n",
+      "Epoch 223/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.7793 - accuracy: 0.7267 - val_loss: 1.8563 - val_accuracy: 0.6117\n",
+      "Epoch 224/300\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.7772 - accuracy: 0.7271 - val_loss: 1.8545 - val_accuracy: 0.6150\n",
+      "Epoch 225/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7751 - accuracy: 0.7287 - val_loss: 1.8527 - val_accuracy: 0.6167\n",
+      "Epoch 226/300\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.7730 - accuracy: 0.7300 - val_loss: 1.8509 - val_accuracy: 0.6183\n",
+      "Epoch 227/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7709 - accuracy: 0.7308 - val_loss: 1.8491 - val_accuracy: 0.6200\n",
+      "Epoch 228/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7688 - accuracy: 0.7308 - val_loss: 1.8473 - val_accuracy: 0.6200\n",
+      "Epoch 229/300\n",
+      "75/75 [==============================] - 1s 10ms/step - loss: 1.7667 - accuracy: 0.7300 - val_loss: 1.8455 - val_accuracy: 0.6200\n",
+      "Epoch 230/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7646 - accuracy: 0.7308 - val_loss: 1.8437 - val_accuracy: 0.6200\n",
+      "Epoch 231/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7625 - accuracy: 0.7308 - val_loss: 1.8419 - val_accuracy: 0.6200\n",
+      "Epoch 232/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7604 - accuracy: 0.7321 - val_loss: 1.8401 - val_accuracy: 0.6233\n",
+      "Epoch 233/300\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 1.7583 - accuracy: 0.7325 - val_loss: 1.8383 - val_accuracy: 0.6250\n",
+      "Epoch 234/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7562 - accuracy: 0.7329 - val_loss: 1.8365 - val_accuracy: 0.6250\n",
+      "Epoch 235/300\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.7542 - accuracy: 0.7321 - val_loss: 1.8347 - val_accuracy: 0.6250\n",
+      "Epoch 236/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.7521 - accuracy: 0.7337 - val_loss: 1.8329 - val_accuracy: 0.6250\n",
+      "Epoch 237/300\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.7500 - accuracy: 0.7342 - val_loss: 1.8311 - val_accuracy: 0.6250\n",
+      "Epoch 238/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7479 - accuracy: 0.7346 - val_loss: 1.8294 - val_accuracy: 0.6267\n",
+      "Epoch 239/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.7459 - accuracy: 0.7346 - val_loss: 1.8276 - val_accuracy: 0.6267\n",
+      "Epoch 240/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7438 - accuracy: 0.7342 - val_loss: 1.8259 - val_accuracy: 0.6267\n",
+      "Epoch 241/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7418 - accuracy: 0.7346 - val_loss: 1.8241 - val_accuracy: 0.6250\n",
+      "Epoch 242/300\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.7397 - accuracy: 0.7346 - val_loss: 1.8224 - val_accuracy: 0.6250\n",
+      "Epoch 243/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7376 - accuracy: 0.7354 - val_loss: 1.8206 - val_accuracy: 0.6233\n",
+      "Epoch 244/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7356 - accuracy: 0.7362 - val_loss: 1.8188 - val_accuracy: 0.6250\n",
+      "Epoch 245/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.7335 - accuracy: 0.7354 - val_loss: 1.8171 - val_accuracy: 0.6267\n",
+      "Epoch 246/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7315 - accuracy: 0.7354 - val_loss: 1.8153 - val_accuracy: 0.6283\n",
+      "Epoch 247/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7294 - accuracy: 0.7371 - val_loss: 1.8136 - val_accuracy: 0.6283\n",
+      "Epoch 248/300\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.7274 - accuracy: 0.7367 - val_loss: 1.8118 - val_accuracy: 0.6283\n",
+      "Epoch 249/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.7254 - accuracy: 0.7383 - val_loss: 1.8101 - val_accuracy: 0.6283\n",
+      "Epoch 250/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7233 - accuracy: 0.7392 - val_loss: 1.8083 - val_accuracy: 0.6300\n",
+      "Epoch 251/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7213 - accuracy: 0.7396 - val_loss: 1.8066 - val_accuracy: 0.6300\n",
+      "Epoch 252/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7192 - accuracy: 0.7404 - val_loss: 1.8048 - val_accuracy: 0.6317\n",
+      "Epoch 253/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7172 - accuracy: 0.7408 - val_loss: 1.8031 - val_accuracy: 0.6317\n",
+      "Epoch 254/300\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.7152 - accuracy: 0.7425 - val_loss: 1.8013 - val_accuracy: 0.6317\n",
+      "Epoch 255/300\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.7131 - accuracy: 0.7425 - val_loss: 1.7995 - val_accuracy: 0.6333\n",
+      "Epoch 256/300\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.7111 - accuracy: 0.7421 - val_loss: 1.7978 - val_accuracy: 0.6317\n",
+      "Epoch 257/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7091 - accuracy: 0.7421 - val_loss: 1.7961 - val_accuracy: 0.6317\n",
+      "Epoch 258/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7071 - accuracy: 0.7433 - val_loss: 1.7943 - val_accuracy: 0.6333\n",
+      "Epoch 259/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7051 - accuracy: 0.7425 - val_loss: 1.7926 - val_accuracy: 0.6333\n",
+      "Epoch 260/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.7031 - accuracy: 0.7433 - val_loss: 1.7909 - val_accuracy: 0.6333\n",
+      "Epoch 261/300\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.7011 - accuracy: 0.7442 - val_loss: 1.7891 - val_accuracy: 0.6333\n",
+      "Epoch 262/300\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.6991 - accuracy: 0.7450 - val_loss: 1.7874 - val_accuracy: 0.6350\n",
+      "Epoch 263/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6971 - accuracy: 0.7442 - val_loss: 1.7857 - val_accuracy: 0.6350\n",
+      "Epoch 264/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.6952 - accuracy: 0.7462 - val_loss: 1.7839 - val_accuracy: 0.6367\n",
+      "Epoch 265/300\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.6932 - accuracy: 0.7462 - val_loss: 1.7822 - val_accuracy: 0.6367\n",
+      "Epoch 266/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6912 - accuracy: 0.7471 - val_loss: 1.7805 - val_accuracy: 0.6367\n",
+      "Epoch 267/300\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.6892 - accuracy: 0.7475 - val_loss: 1.7788 - val_accuracy: 0.6367\n",
+      "Epoch 268/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.6872 - accuracy: 0.7475 - val_loss: 1.7770 - val_accuracy: 0.6367\n",
+      "Epoch 269/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6853 - accuracy: 0.7471 - val_loss: 1.7753 - val_accuracy: 0.6367\n",
+      "Epoch 270/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6833 - accuracy: 0.7496 - val_loss: 1.7736 - val_accuracy: 0.6367\n",
+      "Epoch 271/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6813 - accuracy: 0.7504 - val_loss: 1.7718 - val_accuracy: 0.6350\n",
+      "Epoch 272/300\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 1.6794 - accuracy: 0.7521 - val_loss: 1.7701 - val_accuracy: 0.6367\n",
+      "Epoch 273/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6774 - accuracy: 0.7529 - val_loss: 1.7683 - val_accuracy: 0.6367\n",
+      "Epoch 274/300\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.6754 - accuracy: 0.7529 - val_loss: 1.7666 - val_accuracy: 0.6367\n",
+      "Epoch 275/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6735 - accuracy: 0.7542 - val_loss: 1.7649 - val_accuracy: 0.6367\n",
+      "Epoch 276/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6715 - accuracy: 0.7546 - val_loss: 1.7632 - val_accuracy: 0.6350\n",
+      "Epoch 277/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6696 - accuracy: 0.7571 - val_loss: 1.7615 - val_accuracy: 0.6350\n",
+      "Epoch 278/300\n",
+      "75/75 [==============================] - 0s 7ms/step - loss: 1.6677 - accuracy: 0.7583 - val_loss: 1.7598 - val_accuracy: 0.6367\n",
+      "Epoch 279/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6657 - accuracy: 0.7579 - val_loss: 1.7581 - val_accuracy: 0.6400\n",
+      "Epoch 280/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.6638 - accuracy: 0.7588 - val_loss: 1.7564 - val_accuracy: 0.6417\n",
+      "Epoch 281/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.6619 - accuracy: 0.7583 - val_loss: 1.7547 - val_accuracy: 0.6433\n",
+      "Epoch 282/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6600 - accuracy: 0.7579 - val_loss: 1.7530 - val_accuracy: 0.6433\n",
+      "Epoch 283/300\n",
+      "75/75 [==============================] - 0s 6ms/step - loss: 1.6581 - accuracy: 0.7583 - val_loss: 1.7513 - val_accuracy: 0.6433\n",
+      "Epoch 284/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6562 - accuracy: 0.7588 - val_loss: 1.7496 - val_accuracy: 0.6450\n",
+      "Epoch 285/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6542 - accuracy: 0.7596 - val_loss: 1.7479 - val_accuracy: 0.6450\n",
+      "Epoch 286/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6523 - accuracy: 0.7592 - val_loss: 1.7462 - val_accuracy: 0.6450\n",
+      "Epoch 287/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.6504 - accuracy: 0.7596 - val_loss: 1.7446 - val_accuracy: 0.6450\n",
+      "Epoch 288/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.6485 - accuracy: 0.7608 - val_loss: 1.7429 - val_accuracy: 0.6450\n",
+      "Epoch 289/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6467 - accuracy: 0.7625 - val_loss: 1.7412 - val_accuracy: 0.6450\n",
+      "Epoch 290/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6448 - accuracy: 0.7625 - val_loss: 1.7396 - val_accuracy: 0.6450\n",
+      "Epoch 291/300\n",
+      "75/75 [==============================] - 1s 11ms/step - loss: 1.6429 - accuracy: 0.7633 - val_loss: 1.7379 - val_accuracy: 0.6467\n",
+      "Epoch 292/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.6410 - accuracy: 0.7638 - val_loss: 1.7362 - val_accuracy: 0.6467\n",
+      "Epoch 293/300\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.6391 - accuracy: 0.7650 - val_loss: 1.7346 - val_accuracy: 0.6450\n",
+      "Epoch 294/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.6373 - accuracy: 0.7646 - val_loss: 1.7329 - val_accuracy: 0.6433\n",
+      "Epoch 295/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6354 - accuracy: 0.7658 - val_loss: 1.7313 - val_accuracy: 0.6433\n",
+      "Epoch 296/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.6335 - accuracy: 0.7654 - val_loss: 1.7296 - val_accuracy: 0.6433\n",
+      "Epoch 297/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.6317 - accuracy: 0.7658 - val_loss: 1.7280 - val_accuracy: 0.6433\n",
+      "Epoch 298/300\n",
+      "75/75 [==============================] - 1s 7ms/step - loss: 1.6298 - accuracy: 0.7671 - val_loss: 1.7264 - val_accuracy: 0.6433\n",
+      "Epoch 299/300\n",
+      "75/75 [==============================] - 1s 9ms/step - loss: 1.6280 - accuracy: 0.7675 - val_loss: 1.7247 - val_accuracy: 0.6433\n",
+      "Epoch 300/300\n",
+      "75/75 [==============================] - 1s 8ms/step - loss: 1.6261 - accuracy: 0.7675 - val_loss: 1.7231 - val_accuracy: 0.6433\n"
      ]
     }
    ],
@@ -4065,9 +4273,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 46,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "19/19 [==============================] - 0s 4ms/step - loss: 1.7231 - accuracy: 0.6433\n",
+      "Accuracy : 0.6433333158493042\n"
+     ]
+    }
+   ],
    "source": [
     "loss, accuracy = model.evaluate(X_train[2400:3000], y_cat[2400:3000])\n",
     "print('Accuracy :', accuracy)"
@@ -4082,11 +4299,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 51,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([9, 1, 0, 7, 8, 1, 2, 7, 1, 6])"
+      ]
+     },
+     "execution_count": 51,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "model.predict_classes(X_train[0:10])"
+    "np.argmax(model.predict(X_train[0:10]), axis=1)"
    ]
   },
   {