L3C-PyTorch
L3C-PyTorch copied to clipboard
fab-jul
PyTorch Implementation of the CVPR'19 Paper "Practical Full Resolution Learned Lossless Image Compression"
Hi, thank you for your work. I try to run the l3c.py to test the running time. However, I find that it takes about 6s for encoding/decoding a 512x512 RGB...
I am running into a seg fault error when I try to compress a 16 Bit Image. The problem is in Arithmetic Coding. Any help is appreciated
Will add here what I find. For now: - [ ] "Comparison operations (lt (=), eq (==), ne, (!=) ) return dtype has changed from torch.uint8 to torch.bool": This breaks...
Hello, Thank you very much for sharing the code. It is very helpful. I have a question about your evaluation datasets. Is it possible that you can share both DIV2K...
Hi there, first of all thank you for sharing the code! After I downloaded the Main Model L3C I tried out the compression of an example image with: `python l3c.py...
1. In picture of paper, the picture shows that encode z(s) with model p(z(s) | f(s+1)) . In encoding details, it says encode each channel c of z(s) with C(z(s)...
Allow compilation with PyTorch >=1.2 (testing with 1.6) and GCC 10. This partially addresses #5 I am currently testing this on Arch Linux ( https://aur.archlinux.org/packages/python-pytorch-torchac/ ), will report back later.
dear Dr. Mentzer: I modify your code to a stereo compression version, when I try to encode one of two images, the stages after 0 are all good, but at...
Previously, our preprocessing script saved all training images and validation images as JPGs with a high quality factor of Q=95, downscaled by a factor 0.75. It turns out that the...
Implementation of patch-wise compression. Compression rate slightly worse than full-image compression, but (much) lower resource usage and still better than png. :) Uses 1163 MB GPU memory with patch size...
