The demo.py has too many boxes to incorrect, and the code updated is unstable.

[inFreedom92]

same here

[alen-mask]

same here for coco datasets.

[ma3252788]

the same problem~

[ma3252788]

Changing the threshold is useless

[xafarranxera]

The problem is that no filtering is performed in demo.py. After appending boxes, labels and scores, add this:

dataframe = list(zip(bboxes, labels, bbox_scores))
dataframe = list(filter(lambda x: x[2] >= args.threshold*100, dataframe))

if(len(dataframe) > 0):
    bboxes, labels, bbox_scores = list(zip(*dataframe))
else:
    bboxes, labels, bbox_scores = [], [], []

Best wishes.