Neural Networks with Keras Cookbook

How to do it...

We'll code up the strategy that we listed out as follows (The code file is available as Face_generation.ipynb in GitHub). Note that we'll continue from step 6 in Face generation using a Deep Convolutional GAN section):

1. Generate three vectors (ensure that two images are aligned in one direction and that the other is aligned in the opposite direction by varying the generated noise):

gen_noise = np.random.normal(0, 1, (1, 100))gen_noise2 = np.random.normal(0, 1, (1, 100))gen_noise3 = np.random.normal(0, 1, (1, 100))syntetic_images = Generator.predict(gen_noise4)plt.imshow(deprocess(syntetic_images)[0])plt.axis('off')plt.show()

2. Plot the generated images:

plt.subplot(131)syntetic_images = Generator.predict(gen_noise)plt.imshow(deprocess(syntetic_images)[0]) ...