Anthony Sherbondy

Hi DN-DETR team, Thank you again for sharing your code! I am having problems repeating your training results. I do the following: ``` python -m torch.distributed.launch --nproc_per_node=8 \ main.py -m...

[Here](https://paste-bin.xyz/69102) is the info.txt that logs the exact args and other model info. [Here](https://paste-bin.xyz/69104) is the log.txt of loss info during training. Eval Result: Accumulating evaluation results... DONE (t=23.92s). IoU...

Hmmm, I thought we had removed the window stripping. And if we left it, I'm not so sure what it is useful for now?

Ping.

Thank you for your response! I'll look forward to the full publication then. On Mon, Sep 20, 2021, 9:32 AM weijiawu ***@***.***> wrote: > Thank you for your attention to...

Hello! I see that the complete code has been released, but I still fail to reproduce results on ICDAR TIV challenge of 44% MOTA following steps I listed above. Am...

According to the official ICDAR test [here](https://rrc.cvc.uab.es/?ch=3&com=evaluation&task=1). The results are: MOTA | MOTP | IDF1 | MM | PM | ML 8.25% | 72.43% | 49.54% | 722 | 578...