CompressAI

CompressAI copied to clipboard

ImportError: DLL load failed while importing ans:

1

Hello, I would like to ask you a question about the installation of compressai “Successfully installed compressai-1.2.4.dev0” . I successfully installed cmpressai, but I got the following error when importing:...

WenBingo

No detailed description of the API compress.ans found

3

## Documentation There are no `parameters` or `source` in documentation(https://interdigitalinc.github.io/CompressAI/ans.html) Where I can find that, 3Q.

GraceZhuuu

Image size=(672, 512) cannot be processed by most model

4

Hi, I'm using your colab tutorial to compress some random size images. And I found that when image size=(672, 512), they cannot be processed. Could you fix this bug?

mynotwo

Does CompressAI support direct compression of [y] instead of [y-mean]?

3

As stated, how can we use CompressAI to compress [y] instead of [y-mean]. Furthermore, how can we understand the advantages of compressing [y-mean]? Thank you very much for your answer!!!

zhengxinChenee

Does the number of bits estimated by the neural network same with that obtained by the actrual entropy encoder?

3

As stated, in the evaluation phase, when calling the forward function, the neural network gives you an estimated bit per pixel (bpp) value. I wish to know if this value...

aprilbian

Different bitrates computed using the saved file size and computed using the likelihoods from the entropy model

10

I'm using the EntropyBottleneck module in a factorized prior network. While training, the aux_loss and bpp_loss are decreasing but when I use the trained network to compress and save the...

Reza-Asiyabi

Questions about using entropybottleneck

4

I want to use entropybottleneck to calculate pmf of weights of a trained model. the range of weights value are mostly between (-1, 1), and the number of parameters is...

James89045

Compute pixel-wise bitrate allocation in latent space

3

Hi, Is there a way to compute per-pixel bitrate info in RGB space of the latent variable y or z during evaluation? Regards

danishnazir

Regarding JointAutoRegressiveHierarchicalPriors implementation (mbt2018)

1

Hello, I have a question regarding the implementation of JointAutoRegressiveHierarchicalPriors. I noticed there is something off in the forward() function. ```python y_hat = self.gaussian_conditional.quantize( # Why do you use this...

Indraa145

Hello, in the CompressAI documentation, it is mentioned that "MS-SSIM optimized networks were fine-tuned from pre-trained MSE networks (with a learning rate of 1e-5 for both optimizers)." I want to...

Indraa145