Sovit Ranjan Rath

@tolsicsse I am not sure why you are facing slow down issues. The datasets are created once before the training. Although there is no memory caching but the dataset pipeline...

In that case, you should face any slowness in data loading. It's pretty well-optimized. But surely, let me know in case if you have ideas to optimize it further. I...

@tolsicsse Thanks a lot for the update. It means a lot to see such work from your side. In case you are not comfortable with Git yet, and if you...

I think you forked, created a new branch, and then created a PR. That is the right process. Had you pulled the code recently? I have made some major changes....

@tolsicsse Just to be safe, I am discarding the current PR, maybe you can commit and create a new PR. I am not discarding the PR yet, if you reply...

@tolsicsse I think there is some confusion. I am not saying that I will throw away the contribution. I want to merge it. I just need to be sure that...

Thanks. I will try to merge it by end of the day today.

@GeorgePearse Yes, it handles empty frames. This part in [datasets.py](https://github.com/sovit-123/fasterrcnn-pytorch-training-pipeline/blob/e0ed81307014182d47dd032a2f80a6c49a5fd18c/datasets.py#L333) handles it.

@tolsicsse Thanks for the suggestion. I think Darknet also retains the images without ground truth bounding boxes. I did not know that Detectron 2 also does that. I have been...

@uysalfurkan Can you try reducing the batch size? I think that should solve the issue.