diff --git a/notebooks/Block_5/Jupyter Notebook Block 5 - Object Detection and Segmentation.ipynb b/notebooks/Block_5/Jupyter Notebook Block 5 - Object Detection and Segmentation.ipynb
index 31fa8670b296d6285b139776b1fb72970fd7e5bc..6c81d539393ff5fdc46b5e2aea06db865b5ebd76 100644
--- a/notebooks/Block_5/Jupyter Notebook Block 5 - Object Detection and Segmentation.ipynb	
+++ b/notebooks/Block_5/Jupyter Notebook Block 5 - Object Detection and Segmentation.ipynb	
@@ -839,12 +839,14 @@
     "train_dataset = image_dataset_from_directory(\n",
     "    './train',\n",
     "    image_size=(180, 180),\n",
-    "    batch_size=32)\n",
+    "    batch_size=32,\n",
+    "    label_mode=\"categorical\")\n",
     "\n",
     "validation_dataset = image_dataset_from_directory(\n",
     "    './validation',\n",
     "    image_size=(180, 180),\n",
-    "    batch_size=32)"
+    "    batch_size=32,\n",
+    "    label_mode=\"categorical\")"
    ]
   },
   {
@@ -868,18 +870,6 @@
     "val_features, val_labels = get_features_and_labels(validation_dataset)"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 53,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from tensorflow.keras.utils import to_categorical\n",
-    "\n",
-    "train_labels = to_categorical(train_labels)\n",
-    "val_labels = to_categorical(val_labels)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -1115,18 +1105,6 @@
     "overfitting: we can just reload our saved file."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 67,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Save the features as a Numpy array and the trained model as an h5-file\n",
-    "np.save('./models/bottleneck_features_train.npy', train_features)\n",
-    "np.save('./models/bottleneck_features_validation.npy', val_features)\n",
-    "model.save_weights('./models/bottleneck_fc_model.h5')"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -1207,9 +1185,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import datetime, os\n",
+    "\n",
     "# Load the TensorBoard notebook extension\n",
     "%load_ext tensorboard\n",
     "\n",
+    "logdir = os.path.join(\"logs\", datetime.datetime.now().strftime(\"%Y%m%d-%H%M%S\"))\n",
+    "\n",
     "os.makedirs(logdir, exist_ok=True)\n",
     "%tensorboard --logdir logs"
    ]
@@ -1553,6 +1535,20 @@
     "model_freeze_conv.summary()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import datetime, os\n",
+    "# Load the TensorBoard notebook extension\n",
+    "%load_ext tensorboard\n",
+    "logdir = os.path.join(\"logs\", datetime.datetime.now().strftime(\"%Y%m%d-%H%M%S\"))\n",
+    "os.makedirs(logdir, exist_ok=True)\n",
+    "%tensorboard --logdir logs"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {