Hands-On Deep Learning Algorithms with Python

Visualizing extracted features

Now that we have trained our CNN model, we can see what features our CNN has extracted to recognize the image. As we learned, each convolutional layer extracts important features from the image. We will see what features our first convolutional layer has extracted to recognize the handwritten digits.

First, let's select one image from the training set, say, digit 1:

plt.imshow(mnist.train.images[7].reshape([28, 28]))

The input image is shown here:

Feed this image to the first convolutional layer, that is, conv1, and get the feature maps:

image = mnist.train.images[7].reshape([-1, 784])feature_map = sess.run([conv1], ...