Having recreated the images, let's plot them to get a feel of how they look. First, we will reconstruct the images using the autoencoder instance created earlier:
predicted_imgs = autoencoder.reconstruct(X_test[:100])plt.figure(1, figsize=(10, 10))for i in range(0, 100): im = predicted_imgs[i].reshape((28, 28)) ax = plt.subplot(10, 10, i + 1) for label in (ax.get_xticklabels() + ax.get_yticklabels()): label.set_fontname('Arial') label.set_fontsize(8) plt.imshow(im, cmap="gray", clim=(0.0, 1.0))plt.suptitle('Basic AutoEncoder Images', fontsize=15, y=0.95)plt.savefig('figures/basic_autoencoder_images.png')plt.show()
Let's look at the created images from the neural network:
Basic autoencoder plot of output ...
