Zhonghao

Is the work on the CLR done? I want to use it in a paper.

In fact, I also failed on the CelebA dataset, which I think is caused by RelativisticAverageHinge Loss (I originally thought it was a good enough loss function). But please try...

This error means that your network lacks the definition of the intermediate layer. Please double check the definition of BlurLayer at g_synthesis. Best regards, @huangzh13

You can find the pre-trained model here: https://drive.google.com/file/d/1AcX51sLHX0ks_Ogvtf9EiBxMBwrZMphe/view?usp=sharing

I think it's caused by https://github.com/huangzh13/StyleGAN.pytorch/blob/bce838ecfa34d4de69429af4f7e028b63e52c3fe/models/CustomLayers.py#L183 Fixed random noise is already included in this implementation, but I did not use it in the upper module. You can try to modify...

@akanimax Thanks for your encouragement! I used to refer to the official tensorflow implementation, but did not notice the key points you mentioned (after all, it is hidden in tflib)....

Thanks for your reply! I have checked the latest code and tuned the learning rates. I have also tried the values of `g_lr=0.0003` and `d_lr=0.0003`. But they didn't work. The...

Am I too impatient? I opened this issue because after the same number of epochs, the model with `RelativisticAverageHinge Loss` had got quite good images (both high resolution and low...

I train the model on `CelebA dataset` for only 3 epochs. But the validity of your method has been verified. (16X16)  (128X128)  Your paper and code help me...

Hi, @bemoregt Could you tell me something about your **celebJapan** dataset? Best regards.