UNINEXT

UNINEXT copied to clipboard

i can demo for image. but don't work for video

Traceback (most recent call last): File "projects/UNINEXT/demo.py", line 208, in for vis_frame in tqdm.tqdm(demo.run_on_video(video, args.confidence_threshold), total=num_frames): File "/home/csyun/.local/lib/python3.8/site-packages/tqdm/std.py", line 1195, in iter for obj in iterable: File "/home/csyun/Desktop/UNINEXT/projects/UNINEXT/predictor.py", line 138, in run_on_video yield process_predictions(frame, self.predictor(frame)) TypeError: call() missing 1 required positional argument: 'task'

what is the problem?

@changsubi Hi, for now, we do not have a complete demo script for all video-level tasks. However, you can refer to this issue to find a simple tutorial about demo for MOT.

@MasterBin-IIAU Hi, can you give some demos about RVOS, VOS and MOTS ?

@jiahui1688 Hi, for datasets of these tasks, such as (Ref-)Youtube-VOS and (Ref-)DAVIS, our code will save the mask results. You can check them under outputs dir. We will consider introducing more complicated demo script for supporting taking any video as the input. For MOTS, you can still refer to the instruction given in this issue but you need to change a few lines of code.

@MasterBin-IIAU OK, I'll try to do it. Thank you!

@MasterBin-IIAU Thank you

@MasterBin-IIAU, just wanted to check if video level demos (arbitrary input video) for MOT/MOTS was still something you were considering.

Hi is there an update about that? It will be a pleasure if you release a demo for video segmentation. @ajdroid