EnlightenGAN
EnlightenGAN copied to clipboard
why loss is nan
Hi,
I have input data between 0 and 1, and at the first several epoches, the loss is normal, but then it turned to nan. I cannot find the errors,can you help me?
in base_dataset.py
transform_list += [transforms.ToTensor(), # normalized to [0, 1] transforms.Normalize((0, 0, 0), (1, 1, 1))]
in util.py line 18
image_numpy = np.transpose(image_numpy, (1, 2, 0)) * 255.0