search

Media-Smart / vedatad

A single stage temporal action detection toolbox based on PyTorch
Apache License 2.0
53 stars 14 forks source link

Question about test #8

Open wjn922 opened 3 years ago

wjn922 commented 3 years ago

Hi,

I ran the code of test, and the results are shown as blow. image I wonder whether the repo supports evaluation of mAP of iou@[03:0.7], as reported in the paper. Another question is why the inference needs so much time? Thanks.

C-H-Wong commented 3 years ago

When evaluating different mAP, you only need to pass different iou_thr value to evaluate function here in tools/test.py here. We suggest to save the inference results first (set --out when testing), then run evaluation with different iou_thr, since inference is quite time-consuming.

While comparing to training process which only deal with a clip of 768-frame-length per video, testing would process whole video. Since the model can only process limited length of sequential data, videos are cropped by an overlap ratio of 25% when testing. Besides, processing video data is quite time-consuming already. That's what makes testing process look much more slower than training. After our optimization, the speed of testing process is already lifted a lot.

wjn922 commented 3 years ago

Thanks for your clarification!

wjn922 commented 3 years ago

Since the inference needs so much time, will you support the DDP testing in the future?