Gaurav Parmar

Can you show the error message that you get?

For the custom stats error, it looks like your custom dataset statistics file was not created. Can you check the files in the folder `os.path.join(os.path.dirname(cleanfid.__file__), "stats")`

Looking at this lines you do not need these normalization. [jit detector](https://github.com/NVlabs/stylegan2-ada-pytorch/blob/main/metrics/metric_utils.py#L270) If you look at the forward pass function defined within the torchscript inception model, the normalization applied is...

Hi, Could you provide a minimal code block that can reproduce this error? I have tested the clean-fid computation in a conda env with PyTorch 1.9.0 and CUDA 11.2, this...

I was able to reproduce this error. I found that downgrading the PyTorch version to 1.7 can resolve this error. Let me know if this solution works for you. Regards,...

This issue should be resolved in the current version of clean-fid. Can you show the error trace that caused this?

Hi, Thank you for pointing this out. I have approved the corresponding PR and the new version of the clean-fid should have addressed this issue. Regards, Gaurav

Hi, Thanks for the suggestion! If you can provide me with the details of the dataset and steps to produce them, I can add these statistics too. Regards, Gaurav

Thanks for providing the details. I will take a look at the error with the "legacy_tensorflow" mode. I will verify/test the statistics with some pretrained models and get back to...

Hi, I would be more careful with the steps required in processing the ImageNet images. In the steps you have followed, you are resizing all ImageNet images without applying any...