search

Megvii-BaseDetection / LLA

Official implementation of our paper "LLA: Loss-aware Label Assignment for Dense Pedestrian Detection" in Pytorch.
Apache License 2.0
35 stars 3 forks source link

RetinaNet version of LLA? #1

Open qingswu opened 3 years ago

qingswu commented 3 years ago

Hi, thanks for sharing this excellent work, interesting and elegant idea! I have a question regarding the RetinaNet, do you plan to publish the LLA-RetinaNet code? Interested to do a comparison.

Joker316701882 commented 3 years ago

@qingswu Hello. Thank you for your interest in our work. However, we currently have no plan to release the code of LLA.RetinaNet. But you can implement it by referring to this LLA repo and the following implementation of RetinaNet: https://github.com/Megvii-BaseDetection/cvpods/tree/master/playground/detection/coco/retinanet/retinanet.res50.fpn.coco.multiscale.1x