It's hard to evaluate to the performance of a GAN. How do you even do so? Look into the literature to see what kind of stuff they're doing and why they work.
"As with the previous example, by using a fixed latent space samples tensor and feeding it to the generator at the end of each epoch during the training process, you can visualize the evolution of the training."
It's hard to evaluate to the performance of a GAN. How do you even do so? Look into the literature to see what kind of stuff they're doing and why they work.