Potential label error?
mynameisvinn opened this issue · comments
v commented
since we're training discriminator_on_generator with noise, shouldnt the corresponding label data be a string of 0s instead of 1s?
for i in range(BATCH_SIZE):
noise[i, :] = np.random.uniform(-1, 1, 100)
g_loss = discriminator_on_generator.train_on_batch(noise, [1] * BATCH_SIZE) # shouldnt this be [0] * BATCH_SIZE?
thanks!
Keelin Murphy commented
It should be a string of 1s. You tell the GAN that the incoming data is "real" in order to drive the weights of the generator towards creating a real looking image from the noise. The weights of the discriminator are not changing during this training.