QmapCompression

QmapCompression copied to clipboard

How to install compressAI? I just downloaded it and put it in the QmapCompression folder, but it went wrong.

LemonZhong

NAN value when using the pre-trained model

4

Hello! Great works! What is the reason why I encountered a nan value when using the pre trained model? Looking forward to your reply! 

hongruijia

Hi ! Great Work ! I have just one question : How did you compute the bit allocation map in your article Fig 9 ? Thanks

jjeremy40

Using a target size (torch.Size([1,3,0,500)) that is different to the input size (torch.Size([1, 3,512, 512])). error:the size of tensor a(512) must match the size of tensor b(500) at non-singleton dimension...

linshiyan

Hello, I want to test your code using the pretrained model, but I got this error: FileNotFoundError: [Errno 2] No such file or directory: './data/trainset_coco.csv' Could you please help me...

zara0m

Hello! I have a few questions. 1. how to set the corresponding bpp。 2. is it possible to raise bpp above 1? 3. how should I set it in my...

kerryhhh

I notice that the training time is 2-3 week in the readme. why so long and where is the traing time consumed? Can it reduce the training time to few...

zouwenqin

Some questions about the paper

4

It's amazing to see this work,I'd like to ask some questions. What do the dashed lines and implementations in Figure 6 (b) mean? thank's very much!

CaiShilv

I downloaded the code to the local on the Windows computer, learned it on Pycharm, and after the Python environment was configured, I saw from compressai._CXX import pmf_to_quantized_cdf as _pmf_to_quantized_cdf...

maker-slim

Nan values when using pretrained model

1

Hi, I am getting nan values throughout when I use the pretrained model. Is there anything that needs to be changed? 

GauravYS