CompressAI

CompressAI copied to clipboard

## Bug When I transplant third_party/ryg_rans/rans64.h into Android 64-bit devices, I got such error as: thirdparty\ryg_rans\rans64.h:44:35: error: __int128 is not supported on this target. How can I modify this code...

swaiwi

Support for ONNX export

1

## Feature Enable CompressAI models to be exportable to the ONNX format. ## Motivation I would like to use some of the CompressAI models in a third-party inference framework which...

lbhm

Hi, What should I do if I want to use zero-mean gaussian Entropy Parameters for hyper-latents(like in `y`)? To do that, Can I use the `self.gaussian_conditional` function as it is?...

hyeseojy

ValueError: path '/home/runner/work/CompressAI/CompressAI/compressai/cpp_exts/ops/ops.cpp' cannot be absolute

1

## Bug ## To Reproduce Steps to reproduce the behavior: 1. 1. 1. ## Expected behavior ## Environment Please copy and paste the output from `python3 -m torch.utils.collect_env` ``` -...

zzm422

First of all I want to thank you for your precious work ! I have a question about aux loss. I am trying to train a video compression framework where...

makinyilmaz

Bug when I try to evaluate a model on my own dataset

2

Hi, I think I found a bug when I run the following command (suggested by you): python3 -m compressai.utils.eval_model checkpoint /path/to/images/folder/ -a $ARCH -p $MODEL_CHECKPOINT... The bug is the following:...

AlbertoPresta

Entropy coding

2

First of all, thank you for your work. I trained a model (cheng2020-attn) on my own dataset and then tried to do some tests with your evaluation script python3 train.py...

zjnlxk

Wrong ms-ssim q4 pretrained model for cheng2020-anchor

1

Thanks for your great work! When I download the ms-ssim q4 pretrained model for cheng2020-anchor https://github.com/InterDigitalInc/CompressAI/blob/278f45e6f444448d3c44d973e51f9723768afa18/compressai/zoo/image.py#L149 , it seems that the channel dimension of this checkpoint is 128, which should...

felixcheng97

Distributed Data Parallel support given that DataParallel may be deprecated in the next release of PyTorch

9

Hi @jbegaint @fracape I'm still waiting for CompressAI's DDP support mentioned [here](https://github.com/InterDigitalInc/CompressAI/issues/30#issuecomment-885786036). Could you please reconsider this option again? I think it's a great timing to consider it given that...

yoshitomo-matsubara

JIT not working for (de)compress

3

## Bug I see that you are testing whether JIT of the EntropyBottleneck works (and it does), but JITing the compress/decompress method of an entropy bottleneck does not work. which...

YannDubs