Closed HanGuangXin closed 2 years ago
When training with FP16, annotations of bbox and track_id named as targets will be set to torch.float16 from torch.float32.
targets
But actually, track_id annotations will lose their precision during this procedure, resulting wrong labels for ReID module.
So with the wrong labels, ReID module can not be trained normally, getting extreme low mAP and top-k ranking in person search benchmarks.
After fixing this bug, we can get normal results.
Do you mean that we'd better train with torch.float32?
When training with FP16, annotations of bbox and track_id named as
targets
will be set to torch.float16 from torch.float32.But actually, track_id annotations will lose their precision during this procedure, resulting wrong labels for ReID module.
So with the wrong labels, ReID module can not be trained normally, getting extreme low mAP and top-k ranking in person search benchmarks.
After fixing this bug, we can get normal results.