Deep Learning By Example

Model training

Now let's kick off the training process and see how GANs will manage to generate images similar to the MNIST ones:

train_batch_size = 100num_epochs = 100generated_samples = []model_losses = []saver = tf.train.Saver(var_list = gen_vars)with tf.Session() as sess:    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)                        # Get images, reshape and rescale to pass to D            input_batch_images = input_batch[0].reshape((train_batch_size, 784))            input_batch_images = input_batch_images*2 - 1                        # Sample random noise for G gen_batch_z = np.random.uniform(-1, 1, size=(train_batch_size, gen_z_size)) ...