video inference fails.

[HwanWoongLee]

When I try the following command, I get the following error.

command

python eval.py --trained_model=weights/yolact_edge_54_800000.pth --score_threshold=0.3 --top_k=100 --video_multiframe=2 --trt_batch_size 2 --video=my_video.mp4 --disable_tensorrt

error message

Processing FPS: 38.36 | Video Playback FPS: 0.00 | Frames in Buffer: 334 Traceback (most recent call last):
File "eval.py", line 1280, in
evaluate(net, dataset)
File "eval.py", line 927, in evaluate
evalvideo(net, args.video)
File "eval.py", line 803, in evalvideo
frame['value'] = frame['value'].get()
File "C:\Python\lib\multiprocessing\pool.py", line 768, in get
raise self._value
File "C:\Python\lib\multiprocessing\pool.py", line 125, in worker
result = (True, func(*args, **kwds))
File "eval.py", line 688, in transform_frame
frames = [torch.from_numpy(frame).cuda().float() for frame in frames]
File "eval.py", line 688, in
frames = [torch.from_numpy(frame).cuda().float() for frame in frames]
TypeError: expected np.ndarray (got NoneType)

Environment:

• OS: Windows 10 Pro
• GPU: RTX 3080Ti
• CUDA Version 11.3