CompressAI icon indicating copy to clipboard operation
CompressAI copied to clipboard

A PyTorch library and evaluation platform for end-to-end compression research

Results 54 CompressAI issues
Sort by recently updated
recently updated
newest added

firstly,thank you for your work! i have two gaussian_conditional ,when update model, why one update,another one dont update self.gaussian_conditional = GaussianConditional(None) self.gaussian_conditional_z = GaussianConditional(None) ![image](https://user-images.githubusercontent.com/49899631/224647627-9e3b5fba-0170-4a7a-872f-fdfd9180d381.png) ![image](https://user-images.githubusercontent.com/49899631/224647740-f2f29ae4-af34-4150-a3b4-b45aba88cf81.png) ![image](https://user-images.githubusercontent.com/49899631/224647766-9f73cbbb-ba21-4373-96b5-9a7ba8ea199b.png)

Thanks of your excellent work! Now I wanna to deploy FactorizedPrior on embedded device, and I found EntropyBottleneck in it, but I can not find .compress() and decompress(), so can...

## Feature Why not change it to ```python raise RuntimeError(f'Non-existed directory "{splitdir}"')

I am wondering the result of benchmark of HM vs x265. When I test (run) your code for x265 for HEVC class B BasketballDrive_1920x1080_P420.yuv sequence with QP=32, number of encoding...

Hi, I want to convert the 'ga', 'gs', 'ha', 'hs', 'entropy_bottleneck.compress' and 'gaussian_conditional.compress' from a compressai model into ONNX for export. However, I encountered this problem: 'utf-8' UnicodeDecodeError: codec can't...

Encountered an error from compressai.ans import BufferedRansEncoder, RansDecoder has an error.I don't see this file in the project.

Hi, I see the nice variable rate work on DCC. I want to try it on other models. Could you please provide a training script?

## Bug I have been trying to train ssf2020 model with vimeo90k dataset with quality 8 to compare it with the tests reported in tests folder. but i am not...

How to convert compress and decompress into two ONNXs? Normally, compress and decompress are placed on two devices