Closed jjldr closed 5 years ago
Hi, you are right. I did it in sequential way in order to let more people with limited GPU resources run the code. Current version needs around 2Gb of memory.
I will try to make a parallel version soon (hopefully this weekend).
Thanks for pointing out the problem.
Thank you for your sharing. However, in tracking_on_mot.py, your implementation of siameseRPN is not parallel, which lead to very slow inference time. Could you provide a parallel version. Thank you.