SHL
最近可能会在RK3588之类的板子上测一测，您说的高通联发科的我们项目组暂时没有。算力过低的板子估计不太行，需要剪枝
尽快吧只能说，暂时没空，而且板子暂时不在我这儿。非要说个日期就只能保证5月底之前
this error occurs when 1. there's at least one NAN(not a number) element in your prediction, check by using torch.isnan(tensor). if so, reducing your learning rate might solve your problem,...
If it still cannot be solved and your custom dataset is shareable, you can send your dataset to my email([email protected]) for testing, and I will reply to you before the...
what type is your GPU? I guess that your GPU might not fully support AMP(auto-mixed-precision) training, I test training with fp16 enabled and it works well in RTX30 sesries and...
oh, it might because of the CUDA version. l'm using CUDA 11.1 for RTX3090 in ubuntu18.04. And I'd like to know more about your dataset and your experiments
Sorry, recently I‘m busy for my graduation thesis, and there will be at least 1 month before I totally finish it and start doing this, I guess.
pytorch1.8.1以上带cuda的版本都可以啊
你远程命令行登录的吧，detect.py里面有cv2.imshow，没有图形界面是会报这个错误的
unfortunately we are still trying to fix this, it happens occasionally, you can resume training with last.pth by hand. or you just use "try except" to skip this iter in...