Good tutorial on GANs written in pytorch with explanations?

I am having trouble understand a lot of these pytorch tutorial on GANs. Its hard to dive into their code and understand what each step does without any comments or doctrings to explain things. I feel like going from CNN to GAN in pytorch is a huge jump. What is the best approach to learn GAN with pytorch?

I would suggest to have a look at the code of DCGAN.
It’s a well written code with some comments. The model architectures should be understandable.
The training might be a bit tricky, so let me know, if you want more information about a specific part.

1 Like