Sam Xu

Have you tried training the model without this trick? Is there any significant performance drop? Thank you.

@noovd Did you ensure that the input image is in [0,255] range before you apply normalization? I use the following code transformations = transforms.Compose([ transforms.Scale(224), transforms.ToTensor(), transforms.Lambda(lambda x: x.mul(255)) ])...

Not sure exactly what the issue is, but I suspect something went wrong in parse_json block, you can uncomment [try..except..](https://github.com/samxuxiang/SkexGen/blob/c38f30e8ac40aabfa2a71d6842cc585faa9b9862/utils/convert.py#L49) to get more info.

Thank you for reporting this issue. I will look into this problem and fix it asap.