ShaniGam comments

Results 9 comments of


                                            ShaniGam

warm step

The warm step is not mentioned in the paper. Does it improve the result?

When using no-shared = False, the process is blocked

Anyone found a solution?

When using no-shared = False, the process is blocked

It's the exact same problem as in: https://github.com/pytorch/pytorch/issues/2496 It's stuck on the ConvND call: `f = ConvNd(_pair(stride), _pair(padding), _pair(dilation), False, _pair(0), groups, torch.backends.cudnn.benchmark, torch.backends.cudnn.enabled) return f(input, weight, bias)`

How to generate different "styles"?

@wottpal did you manage to generate good images with different styles?

I ran the pix2pixHD code, the training results are good, however the test results are very bad.

Has anyone managed to find the problem? I use the latest code and has the same issue (good results when training, bad results when testing)

Bad results when continue training

I tried that as well, same results.

Bad results when continue training

I'm sure it's the correct size because I stopped the experiment and ran it again right away. Besides, if it generates good images that are > 64, shouldn't generate good...

Bad results when continue training

Unfortunately no but I stopped working on that.