EdSong

Results 97 comments of 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.

> ![image](https://user-images.githubusercontent.com/38450078/198761994-60a55b08-ef99-41ff-955a-d00d497f98b2.png) 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...

> ![image](https://user-images.githubusercontent.com/38450078/199383329-7d825aed-1ba4-4da2-a13e-76e8bdf982fd.png) 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...