CompressAI

CompressAI copied to clipboard

Ubuntu compressed images can't be decoded properly in Windows

1

I've configured Compressai on both Ubuntu and Windows. they both encode and decode fine on their respective systems. But the bin files compressed by Ubuntu are not decoded properly in...

GZLiao-sysu

How to .update() a GaussianConditional entropy model and properly call .compress() and .decompress()?

2

Hello! I'm trying to train my own custom autoencoder model while integrating `EntropyBottleneck` and `GaussianConditional`. Here's a snippet of my class: ``` class AEWithEntropy(nn.Module): def __init__(self, freeze_base=True): super().__init__() self.base =...

johnli25

 I've been stuck here all along, and soon the following error will appear： This error originates from a subprocess, and is likely not a problem with pip.

paomian001

Sorry to bother you, but I have some stupid questions. I noticed that the `_compress_ar` function in the `JointAutoregressiveHierarchicalPriors` model uses two for-loops during the encoding process to predict the...

chunbaobao

Questions about the PSNR result of the project

3

I want to know how can I get the result like the picture in the project. I notice that some of them can exceed 40dB, but i can just only...

BeamReflection

I want to know the parameters accepted by EntropyBottleneck and GaussianConditional and their processing. Can you explain it a little bit? And what is the EntropyCoder used in this project?...

BeamReflection

Allow returning latent space y or y_hat to allow variable rate modification

2

## Feature Please allow user to specify whether y_hat (and possibly also y) be returned from the forward and compress methods of all codec families. i.e.: ``` class SimpleVAECompressionModel.forward(CompressionModel): ......

picagrad

https://github.com/InterDigitalInc/CompressAI/blob/master/compressai/utils/bench/codecs.py#L821 'img' is a file address for an image here, but this line of code treats it as data for the image The correct code should be: `arr = np.asarray(self._load_img(img))`

wp10005

About 12-bit image compression

3

I created a function to normalize a 12-bit image to the range [0,1] and use it as input for network. I wonder whether this is sufficient or if certain parameters...

YuKDseele

About the y_bpp and the Gaussian entropy model

4

Hello, I have a question about **y_bpp** and normalization. In the implementation of the Gaussian entropy model in CompressAI, **y_bpp** is computed by estimating the likelihood after normalizing the input:...

YuKDseele