DiffusionDet
DiffusionDet copied to clipboard
Too many boxes when using demo.py with --video-input video.mp4
Hello! Thanks for your great working!
I run demo.py with --video-input. But there are too many boxes in the generated results. Please tell me what I should do.
I Adjust the threshold value in the detector.py. This problem cannot be solved.
I also run demo.py with --input image.jpg, the results seems correct.
I really want to know why?
PS: trained on COCO and LVIS
@BrainPotter Hello, i have same issue before. I checked the predictor.py and i found that on video there is no score_threshold filtering. you add it like this.
Thank you very much!