Linson

> 为什么用自己训练的权重来测试视频会出现这种错呢？ Traceback (most recent call last): File "demo.py", line 164, in for vis_frame in tqdm.tqdm(demo.run_on_video(video, args.confidence_threshold), total=num_frames): File "/root/anaconda3/envs/cyy/lib/python3.8/site-packages/tqdm-4.65.0-py3.8.egg/tqdm/std.py", line 1178, in **iter** for obj in iterable: File "/remote-home/cs_cst_yy/cyy/SparseInst-main/sparseinst/d2_predictor.py",...

I find out the reason is that the first image and second image always take lots of inference time, so the FPS calculation should ignore the first and second image,...