Now that we have the model built, we can kick off the learning process by generating random batches form the MNIST dataset and feed them to the optimizer defined earlier.

Let's start off by creating the session variable; it will be responsible for executing the computational graph that we defined earlier:

sess = tf.Session()
num_epochs = 20
train_batch_size = 200
sess.run(tf.global_variables_initializer())

for e in range(num_epochs):
    for ii in range(mnist_dataset.train.num_examples//train_batch_size):
        input_batch = mnist_dataset.train.next_batch(train_batch_size)
        input_images = input_batch[0].reshape((-1, 28, 28, 1))
        input_batch_cost, _ = sess.run([model_cost, model_optimizer], feed_dict={inputs_values: input_images,targets_values: input_images})

        print("Epoch: {}/{}...".format(e+1, num_epochs),
              "Training loss: {:.3f}".format(input_batch_cost))

Output:
.
.
.
Epoch: 20/20... Training loss: 0.102
Epoch: 20/20... Training loss: 0.099
Epoch: 20/20... Training loss: 0.103
Epoch: 20/20... Training loss: 0.102
Epoch: 20/20... Training loss: 0.100
Epoch: 20/20... Training loss: 0.101
Epoch: 20/20... Training loss: 0.098
Epoch: 20/20... Training loss: 0.103
Epoch: 20/20... Training loss: 0.104
Epoch: 20/20... Training loss: 0.103
Epoch: 20/20... Training loss: 0.098
Epoch: 20/20... Training loss: 0.102
Epoch: 20/20... Training loss: 0.098
Epoch: 20/20... Training loss: 0.099
Epoch: 20/20... Training loss: 0.103
Epoch: 20/20... Training loss: 0.104
Epoch: 20/20... Training loss: 0.101
Epoch: 20/20... Training loss: 0.105
Epoch: 20/20... Training loss: 0.102
Epoch: 20/20... Training loss: 0.102
Epoch: 20/20... Training loss: 0.100
Epoch: 20/20... Training loss: 0.099
Epoch: 20/20... Training loss: 0.102
Epoch: 20/20... Training loss: 0.102
Epoch: 20/20... Training loss: 0.104
Epoch: 20/20... Training loss: 0.101
Epoch: 20/20... Training loss: 0.099
Epoch: 20/20... Training loss: 0.098
Epoch: 20/20... Training loss: 0.100
Epoch: 20/20... Training loss: 0.101
Epoch: 20/20... Training loss: 0.100
Epoch: 20/20... Training loss: 0.100
Epoch: 20/20... Training loss: 0.101
Epoch: 20/20... Training loss: 0.098
Epoch: 20/20... Training loss: 0.101
Epoch: 20/20... Training loss: 0.103
Epoch: 20/20... Training loss: 0.103
Epoch: 20/20... Training loss: 0.102
Epoch: 20/20... Training loss: 0.101
Epoch: 20/20... Training loss: 0.100
Epoch: 20/20... Training loss: 0.101
Epoch: 20/20... Training loss: 0.102
Epoch: 20/20... Training loss: 0.103
Epoch: 20/20... Training loss: 0.103
Epoch: 20/20... Training loss: 0.103
Epoch: 20/20... Training loss: 0.099
Epoch: 20/20... Training loss: 0.101
Epoch: 20/20... Training loss: 0.096
Epoch: 20/20... Training loss: 0.104
Epoch: 20/20... Training loss: 0.104
Epoch: 20/20... Training loss: 0.103
Epoch: 20/20... Training loss: 0.103
Epoch: 20/20... Training loss: 0.104
Epoch: 20/20... Training loss: 0.099
Epoch: 20/20... Training loss: 0.101
Epoch: 20/20... Training loss: 0.101
Epoch: 20/20... Training loss: 0.099
Epoch: 20/20... Training loss: 0.100
Epoch: 20/20... Training loss: 0.102
Epoch: 20/20... Training loss: 0.100
Epoch: 20/20... Training loss: 0.098
Epoch: 20/20... Training loss: 0.100
Epoch: 20/20... Training loss: 0.097
Epoch: 20/20... Training loss: 0.102

After running the preceding code snippet for 20 epochs, we'll get a trained CAE, so let's go ahead and test this model by feeding similar images from the MNIST dataset:

fig, axes = plt.subplots(nrows=2, ncols=10, sharex=True, sharey=True, figsize=(20,4))
input_images = mnist_dataset.test.images[:10]
reconstructed_images = sess.run(decoded_layer, feed_dict={inputs_values: input_images.reshape((10, 28, 28, 1))})

for imgs, row in zip([input_images, reconstructed_images], axes):
    for img, ax in zip(imgs, row):
        ax.imshow(img.reshape((28, 28)), cmap='Greys_r')
        ax.get_xaxis().set_visible(False)
        ax.get_yaxis().set_visible(False)

fig.tight_layout(pad=0.1)

Output:

Figure 9: Examples of the original test images (first row) and their constructions (second row) using the convolution autoencoder