XiaoqiangZhou

Did you verify the code in pytorch version?

1

The Network archtecture of Discriminator is strange in "MNIST_EDGE" task. Why the number of ouput channel is 2? When I train the `train_cogan_mnist.py`, the result is awful. It seems Generator...

A question about discriminator design

1

Hi, it seems you only use a PatchGAN as your discriminator, which is different from conventional method that use both global and local discriminator. Could you please explain why you...

Code Release

6

Thanks for sharing such a great work! I'm looking forward to the code release. It would be better if the code is implemented with PyTorch. Thanks!

Problem in contextual attention module

1

Thanks for your reimplementation. When I run the test_contextual_attention function in the `network.py`. Error occured. `RuntimeError: Given transposed=1, weight of size 4096 3 4 4, expected input[1, 4032, 166, 250]...

Hi, I'm reading your CSA-inpainting work recently. The most impressive novelty of this work is that CSA layer takes use of information from not only known regions, but also generated...

Some questions about `networks_stylegan.py`

4

Thanks for your reimplementation! 1. In networks_stylegan.py, line 107 `f = f[:, :, ::-1, ::-1]`, I think you should consider use `f = torch.flip(f, [2, 3])` 2. In networks_stylegan.py, line...

In 'models/graph_memory.py', line 274. i.e., the forward function of class ' Memory'. `m_out_all[:, :, x, :, :] = hiden_state` It seems that the updated memory cell `m_out_all` will not influence...

Dear researcher, Thanks for sharing this great work. A question about the code is that the mixed precision training (i.e., amp) is disabled. Does the amp training lead to training...

Thanks for contributing such a great work. Why use 'zero_module' in the last convolution layer?

About the implementation on multi-scale condition.

1

Thanks for sharing this great work. In the paper, you mentioned that "transfer rich multi-scale texture patterns from the source image distribution to the noise prediction" How ever, in the...