EdSong
EdSong
> Thx for your work, could you share your trained weights? sorry for forgetting to reply. I have uploaded the checkpoints.
it is weird. Why there is a class "-1".
> I guess because TXT file annotations way is different, I start from 0 annotation. However, after I modified the labeling file, the detection effect was not very ideal. The...
Maybe you can use pycharm to debug it``````I do not know why this happens.
I always train 300 epochs. Maybe it is because it has not converged. You can check the mAP curve on tensorboard, and find the best performance.
>  The program killed twice when I came to 84 epochs, do you have any idea about that? QAQ sometimes I would happen like this, and I don't know...
>  I set the setting all the same with yours, but there is only 46 mAP on ori,it is much less than mAP=56 in your paper. Is that normal?Or...