It's time to start training this deeper network, which in turn will take more time to converge by reconstructing noise-free images from the noisy input.

So let's start off by creating the session variable:

sess = tf.Session()

Next up, we will kick off the training process but for more number of epochs:

num_epochs = 100
train_batch_size = 200

# Defining a noise factor to be added to MNIST dataset
mnist_noise_factor = 0.5
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)
        
        # Getting and reshape the images from the corresponding batch
        batch_images = input_batch[0].reshape((-1, 28, 28, 1))
        
        # Add random noise to the input images
        noisy_images = batch_images + mnist_noise_factor * np.random.randn(*batch_images.shape)
        
        # Clipping all the values that are above 0 or above 1
        noisy_images = np.clip(noisy_images, 0., 1.)
        
        # Set the input images to be the noisy ones and the original images to be the target
        input_batch_cost, _ = sess.run([model_cost, model_optimizer], feed_dict={inputs_values: noisy_images,
                                                         targets_values: batch_images})

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

Output:
.
.
.
Epoch: 100/100... Training loss: 0.098
Epoch: 100/100... Training loss: 0.101
Epoch: 100/100... Training loss: 0.103
Epoch: 100/100... Training loss: 0.098
Epoch: 100/100... Training loss: 0.102
Epoch: 100/100... Training loss: 0.102
Epoch: 100/100... Training loss: 0.103
Epoch: 100/100... Training loss: 0.101
Epoch: 100/100... Training loss: 0.098
Epoch: 100/100... Training loss: 0.099
Epoch: 100/100... Training loss: 0.096
Epoch: 100/100... Training loss: 0.100
Epoch: 100/100... Training loss: 0.100
Epoch: 100/100... Training loss: 0.103
Epoch: 100/100... Training loss: 0.100
Epoch: 100/100... Training loss: 0.101
Epoch: 100/100... Training loss: 0.099
Epoch: 100/100... Training loss: 0.096
Epoch: 100/100... Training loss: 0.102
Epoch: 100/100... Training loss: 0.099
Epoch: 100/100... Training loss: 0.098
Epoch: 100/100... Training loss: 0.102
Epoch: 100/100... Training loss: 0.100
Epoch: 100/100... Training loss: 0.100
Epoch: 100/100... Training loss: 0.099
Epoch: 100/100... Training loss: 0.098
Epoch: 100/100... Training loss: 0.100
Epoch: 100/100... Training loss: 0.099
Epoch: 100/100... Training loss: 0.102
Epoch: 100/100... Training loss: 0.099
Epoch: 100/100... Training loss: 0.102
Epoch: 100/100... Training loss: 0.100
Epoch: 100/100... Training loss: 0.101
Epoch: 100/100... Training loss: 0.102
Epoch: 100/100... Training loss: 0.098
Epoch: 100/100... Training loss: 0.103
Epoch: 100/100... Training loss: 0.100
Epoch: 100/100... Training loss: 0.098
Epoch: 100/100... Training loss: 0.100
Epoch: 100/100... Training loss: 0.097
Epoch: 100/100... Training loss: 0.099
Epoch: 100/100... Training loss: 0.100
Epoch: 100/100... Training loss: 0.101
Epoch: 100/100... Training loss: 0.101

Now we have trained the model to be able to produce noise-free images, which makes autoencoders applicable to many domains.

In the next snippet of code, we will not feed the row images of the MNIST test set to the model as we need to add noise to these images first to see how the trained model will be able to produce noise-free images.

Here I'm adding noise to the test images and passing them through the autoencoder. It does a surprisingly great job of removing the noise, even though it's sometimes difficult to tell what the original number is:

#Defining some figures
fig, axes = plt.subplots(nrows=2, ncols=10, sharex=True, sharey=True, figsize=(20,4))

#Visualizing some images
input_images = mnist_dataset.test.images[:10]
noisy_imgs = input_images + mnist_noise_factor * np.random.randn(*input_images.shape)

#Clipping and reshaping the noisy images
noisy_images = np.clip(noisy_images, 0., 1.).reshape((10, 28, 28, 1))

#Getting the reconstructed images
reconstructed_images = sess.run(decoding_layer, feed_dict={inputs_values: noisy_images})

#Visualizing the input images and the noisy ones
for imgs, row in zip([noisy_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: