David Goldstein

Thanks bro! This is incredibly helpful and time saving. Thanks for sharing! Tip for Nvidia 3000 series users, replace `conda install -c pytorch pytorch=1.9.1 torchvision cudatoolkit=10.2` with `pip install torch==1.9.1+cu111...

I am having the same issue! When I use the ADE dataset images it trains with no issues but when I use my own, with the same bit depth, it...

I think figured it out. It's basically an overload error I think. Decreasing the amount of images may help with that error. I don't know why a lower batch size...

This is a big issue. I can't move forward without these files.

I found a solution! The problem is that the author is using a pretrained state which wants to access the already trained model. The only issue is that they didn't...

Are there any specific repos I can be referred to?

I am having the same issue...

> After some really tedious debugging and tackling various hidden problems, I managed to compile the whole module. This is the end result: https://github.com/DeXtmL/bitsandbytes-win-prebuilt > > The binaries are compiled...

> > After some really tedious debugging and tackling various hidden problems, I managed to compile the whole module. This is the end result: https://github.com/DeXtmL/bitsandbytes-win-prebuilt > > The binaries are...

@nfsergiu Unfortunately not, though I did have success with another repo called [DECA](https://github.com/yfeng95/DECA)