Rex Cheng

I cannot peek into your file system and know what is in each folder. One potential reason is that you are not using all the frames in YouTubeVOS (i.e., https://drive.google.com/drive/folders/16uw2j3o8Pi2xhvgGopYMKyjKtzV9RQ6c)

See here https://github.com/hkchengrex/Tracking-Anything-with-DEVA/blob/main/docs/EVALUATION.md#general-arguments Use `--amp`

I am not sure if I understand your question. If you just want to run SAM, you should use https://github.com/facebookresearch/segment-anything

I haven't had the time to test it yet.

I don't have a Mac device and cannot test it but I suppose you can replace all the `.cuda()` and `cuda.amp` calls with mps equivalent.

If you try the example video, i.e., ``` python demo/demo_with_text.py --chunk_size 4 \ --img_path ./example/vipseg/images/12_1mWNahzcsAc \ --amp --temporal_setting semionline \ --size 480 \ --output ./example/output --prompt person.hat.horse ``` , it...

Ref: https://github.com/hkchengrex/Cutie/issues/14

The warning means that the detector cannot detect anything. Can you try re-installing Grounded-DINO/SAM? It seems like a problem on either one of these dependencies.

Can it be a compilation error? If it is compiled for 2060 it would not work for different SM

Please feel free to re-open if there are any updates.