Bosheng (Daniel) Zhang

我在原代码model/detector.py的forward function里修改，因为我看这里有两个tensor output，但他们size不一样   我也不是很确定是不是修改这里，求指导~ Any helps will be appreciated!!

issue fixed! Can check out my new pull request in the original work. Hope it helps! https://github.com/hpc203/yolo-fastestv2-opencv/issues/5#issuecomment-979707357

issue fixed! Can check out my new pull request in the original work. Hope it helps! https://github.com/dog-qiuqiu/Yolo-FastestV2/pull/44#issue-1064116145

I avoid the issue by using 'final_state.pth'. instead, I used 'epoch_240.pth'. Don't know why but I am running now.

 Hi leidi1989, after I changed `checkpoint_file = args.weights[0]` in test.py, it raised me another error as shown above, any clues? Thanks in advance!

> I also encounter this problem when I train my lane line segmentation, the trained detection head gets worse. Hi, I retrained my model with an encoder and single detection...

> 1. Change default parameters of --device to “cuda device” >  > 2. Run the demo.py >  the 'Cuda available' is the description, you should choose from 0,1,2...

 Is that because I freezed to train the encoder also?

> Errors like this is due to model mismatch between pytorch and tensorrt. You can follow the readme to use the matched version, and try official model first. > >...

I am having the same issue.