Some issues in demo.py

[dhiyu]

In function detect of file demo.py, the codes
for i in range(2): start = time.time() boxes = do_detect(m, sized, 0.5, num_classes, 0.4, use_cuda) finish = time.time() if i == 1: print('%s: Predicted in %f seconds.' % (imgfile, (finish - start)))
My problem is why we need to conduct these codes two times. Thanks~ @Tianxiaomo

[ersheng-ai]

I think it is maybe because the first iteration usually consumes longer time and inaccurate for speed estimation.

[Tianxiaomo]

warmup