From 41726926a53fb13d405f3be1b790e4f1daa2cbff Mon Sep 17 00:00:00 2001
From: Mirko Birbaumer <mirko.birbaumer@hslu.ch>
Date: Wed, 9 Dec 2020 21:31:42 +0000
Subject: [PATCH] Project extension - pose estimation
pose estimation - deeplabcut
---
...s to Exercises Block 4 - Convolutional Neural Networks.ipynb | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/notebooks/Block 4/Solutions to Exercises Block 4 - Convolutional Neural Networks.ipynb b/notebooks/Block 4/Solutions to Exercises Block 4 - Convolutional Neural Networks.ipynb
index 9b5b486..3913419 100644
--- a/notebooks/Block 4/Solutions to Exercises Block 4 - Convolutional Neural Networks.ipynb
+++ b/notebooks/Block 4/Solutions to Exercises Block 4 - Convolutional Neural Networks.ipynb
@@ -749,7 +749,7 @@
"\n",
"In the cell below, create a convolutional neural network that consists of 3 convolution blocks. Each convolutional block contains a `Conv2D` layer followed by a max pool layer. The first convolutional block should have 16 filters, the second one should have 32 filters, and the third one should have 64 filters. All convolutional filters should be 3 x 3. All max pool layers should have a `pool_size` of `(2, 2)`.\n",
"\n",
- "After the 3 convolutional blocks you should have a flatten layer followed by a fully connected layer with 512 units. The CNN should output class probabilities based on 5 classes which is done by the **softmax** activation function. All other layers should use a **relu** activation function. You should also add Dropout layers with a probability of 20%, where appropriate."
+ "After the 3 convolutional blocks you should have a flatten layer followed by a fully connected layer with 512 units. The CNN should output class probabilities based on 5 classes which is done by the `softmax` activation function. All other layers should use a `relu` activation function. You should also add Dropout layers with a probability of 20%, where appropriate."
]
},
{
--
GitLab