Practical Convolutional Neural Networks

Adding the optimizer

We need to update the generator and discriminator variables separately. So, first get all the variables of the graph and then, as we explained earlier, we can get only generator variables from the generator scope and, similarly, discriminator variables from the discriminator scope:

# Optimizerslearning_rate = 0.002# Get the trainable_variables, split into G and D partst_vars = tf.trainable_variables()g_vars = [var for var in t_vars if var.name.startswith('generator')]d_vars = [var for var in t_vars if var.name.startswith('discriminator')]d_train_opt = tf.train.AdamOptimizer(learning_rate).minimize(d_loss, var_list=d_vars)g_train_opt = tf.train.AdamOptimizer(learning_rate).minimize(g_loss, var_list=g_vars)

To train the ...