Rohit K Bharadwaj

wow these people are the best!! more power to you guys @lixunsong!! Thank you for truly open sourcing the knowledge.

So, I made a change in this except block to `except Exception as e:`, and it did fix the problem. I think it needs to be changed in the source...

Also, I'm still getting errors with the current code even after passing `pad_frames = True` Could you please help? Error logs: ``` IndexError: Caught IndexError in DataLoader worker process 1....

Sent discord request. Are you able to use the provided code for dataloader in multi-GPU environment?

Any fix for this? I seem to have similar problem and I have described it in https://github.com/coder/code-server/issues/6619 I hope this can be fixed..

Hello, It seems to be a problem with the Pytorch/CUDA/CUDNN libraries, and not specifically with the code in this repo AFAIK. I did search about it, and seems to be...

Hello, sorry to hear that. Could you please try uninstalling Pytorch and trying to install it again manually, maybe using a different version? You can also try to install Detectron2...

@ralpyna you can also ensure that when you're running the code, the GPU memory is empty. Type "nvidia-smi" and verify that no other process is occupying the GPU. The error...

Hello, thank you for your interest in our work. Our work is a training-free approach which utilizes pre-trained foundational models to complement Mask-RCNN. To use your custom dataset, I would...

You can use our approach on your custom dataset, you can refer to the linked docs above, and also read the paper once. Our approach does not require any training,...