some tiny issues in GAN

[ivanjacobs]

Hey great read and great code.
I stumbled on some tiny issues when running the GAN:
in def train_discriminator
the:

else:
            idx = np.random.randint(0, x_train.shape[0], batch_size)
            true_imgs = x_train[idx]

should be

else:
           idx = np.random.randint(0, x_train[0].shape[0], batch_size)
            true_imgs = x_train[0][idx]

as it comes back with x at [0] and y at [1]
when running the train I had to use:

graph = tf.get_default_graph()
with graph.as_default():
     gan.train(........

as it was complaining about tensors not being part of the graph. that seems to be a Keras issue.

[davidADSP]

Can you let me know which notebook you're running to see this error?

[davidADSP]

I can't replicate this error - if you let me know which notebook produces the error or link to a reproducible example, I'll reopen.