pytorch-msssim
pytorch-msssim copied to clipboard
VainF
Fast and differentiable MS-SSIM and SSIM for pytorch.
Image size should be larger than 160 due to the 4 downsamplings in ms-ssim.How should I change it?
I just check PEP-8 by brain, maybe not passing the autopep8 formatter. Code has already passed all the pylance basic check. I'll remark some suggestions inside code diff.
What does T mean in (N,C,[T,]H,W) in ms_ssim?
Quick question on the output range. Does the SSIM implementation output number of range [0;1] or [-1;1] instead as described in the original SSIM paper http://www.cns.nyu.edu/pub/lcv/wang03-reprint.pdf ?
nonnegative_ssim added for MS_SSIM with True as default, so there won't be any change in the default behaviour.
When I input 2D grayscale image ,i report this. ValueError: Input images should be 4-d or 5-d tensors, but got torch.Size([256, 256]) Therefore,I change the input dimension to 4D(1,1,256,256),but i...
It seems that whether the class SSIM/MS_SSIM or the function ssim/msssim are all unsupported for the input with 1 channel. When I fed the ssim function with input array of...
Hi, Thanks for this tool. I use both pytorch_mssim.ssim and skimage.measure.compare_ssim to compute ssim, but the results are different. For example, ssim evaluation on an image sequence: pytorch_msssim.ssim: [0.9655, 0.9500,...
size_average=False returns a tensor containing individual SSIM scores instead of returning their sum
Hi, I'm not sure if this behavior is intended or not but for a batch of 64 images, when I set size_average=False, i get a tensor of size 64 with...
What are your thoughts about extending the library to include the following metrics: - 3-SSIM - 3-MS-SSIM - G-SSIM - G-MS-SSIM - 3-G-SSIM - 3-G-MS-SSIM - 4-SSIM - 4-MS-SSIM -...
