KL-Loss
KL-Loss copied to clipboard
Any plans for PyTorch version with MMDetection?
Hi Yihui,
This method is hugely interesting and I would like to incorporate it in my research. Do you have any plans to release a PyTorch version of the code? It would be very useful to the community.
Thank you!
@LiJunnan1992 Do you incorporated successfully?
@LittleBoy7 Not yet...
@LittleBoy7 @LiJunnan1992 Hi, I reimplemented kl-loss in with my own project Stronger-yolo-pytorch. You may find some help here.
@wlguan This is awesome! I'll add a link to your repo in the readme
@wlguan I want to reimplemented KL loss , but I cannot find your project( Stronger-yolo-pytorch), could you please give me some help?
@wlguan I want to reimplemented KL loss , but I cannot find your project( Stronger-yolo-pytorch), could you please give me some help?
here's a fork https://github.com/yihui-he/Stronger-yolo-pytorch
Hi, I have implemented a pytorch version of KL-Loss with MMDetection in my project KL-Loss-pytorch. The reproduced results are as follows:
KL Loss | Var Vote | soft-NMS | AP (Original Paper) | AP (Reproduced) |
---|---|---|---|---|
:x: | :x: | :x: | 37.9 | 38.4 |
:heavy_check_mark: | :x: | :x: | 38.5 | 39.2 |
:heavy_check_mark: | :heavy_check_mark: | :x: | 38.8 | 39.8 |
:heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | 39.2 | 40.2 |