How can I track the loss of a DCGAN

Question

I'm following this https://www.tensorflow.org/tutorials/generative/dcgan#the_discriminator but i'm using my own pictures. I wanted someway to look at loss, accuracy, and/or anything else that might be useful to look at in order to optimize the network. I mostly only care about loss for now. I have tried to look at similar examples that include a way to show loss like this https://machinelearningmastery.com/practical-guide-to-gan-failure-modes/. However, I still don't understand how to do it for the tensorflow DCGAN example.

To be clear I have a loss function. I just can't figure out how to print it out to actually see what's going on.

Oh i should mention i am having it print the "decision" for each generated image in each epoch. So I know how to do that.

Answer 1

I ended up just putting.

noise = tf.random.normal([BATCH_SIZE, noise_dim])
generated_images = generator(noise, training=True)
real_output = discriminator(image_batch, training=True)
fake_output = discriminator(generated_images, training=True)
gen_loss = generator_loss(fake_output)
disc_loss = discriminator_loss(real_output, fake_output)
print(gen_loss)
print(disc_loss)

into the for loop within the train function.