Open ToTheBeginning opened 6 years ago
I see many code like this:fake_data = G(noise).detach()
fake_data = G(noise).detach()
But in your most code, there is no detach, so is it just ok to omit it ?
https://github.com/pytorch/examples/issues/116
I see many code like this:
fake_data = G(noise).detach()
But in your most code, there is no detach, so is it just ok to omit it ?