Jianhua Yang

@tianzhi0549 Thank you so much for open-sourcing such an excellent project. Recently, I'm trying to reproduce FCOS, and I want to understand the AP changes during training, so may I...

很感谢OTA这个工作被提出，省去了FCOS中的很多人工参数的麻烦。 这里我有一个小疑问，就是使用OTA的时候，训练期间的正样本数量是不是会比原生的FCOS少一些？还是说只在训练的早期会少（可能是这个时候模型还没有收敛到一个比较好的性能，致使不好的预测可能会占比多一些）？ 期待作者的解答~

About NAN during training

1

@chensnathan I think the following passage may be the main cause of the NAN problem: normalized_cls_score = cls_score + objectness - torch.log( 1. + torch.clamp(cls_score.exp(), max=self.INF) + torch.clamp( objectness.exp(), max=self.INF))...

A stronger YOWO achieved by us.

4

Thanks for the open source of YOWO, a real-time method in spatio-temporal action detection task. Recently, I follow this repo. to reimplemented ```YOWO``` and achieve better performance, as shown in...

Dear friends, I may have explored the structure of GELAN-S (similar to YOLOv9-S), and its model parameters and FLOPs are very close to the results reported in the paper. Please...