poplar
poplar
i have also the problem, ModuleNotFoundError: No module named 'nms._ext' Can you help me solve the problem?
i see #322 and try do the solution in my work.
use torch.nn.utils.clip_grad_norm_ function can solve the problem and add the a small learning rate
in the training time, has some warning, the follow picture show the warning. the warn one:  the warn two:  the warn three: 
你这个加速的问题现在解决了吗@txy00001
您好前辈@wangshuang-jiayou，请问自己的数据集是怎么准备的？
when i use uperhead_transformer net, I have also the problem, and look for the problem in the internet, other people said a lot of method, but one of all can't...
Hi@uniquecdmx , 请问你这个问题解决了吗，我用pp-human也是同样的问题，第一帧卡住，没有报错，
> > Hi@uniquecdmx , 请问你这个问题解决了吗，我用pp-human也是同样的问题，第一帧卡住，没有报错， > > 解决了，是因为我没有开rtsp推流服务 我也开了rtsp服务，但是检测后的视频流推着推着就变慢了，从speed1.x降到0.5x左右，视频也会变得很卡。