Reproducibility Issues with SSIM and MS-SSIM as Loss Functions

[batman47steam]

I would like to ask about the reproducibility issues with SSIM and MS-SSIM. I am considering using MS-SSIM as a loss function to supervise my model's training. However, I have noticed that when using pytorch_msssim for SSIM and MS-SSIM, the training loss fluctuates with each run. In contrast, using the SSIM implementation from this source does not result in such fluctuations. Have you encountered similar issues, or do you have any suggestions to ensure consistent loss during training?