LI Wentong

Thanks for your reply. I have resolved it.

Hello, I know that you are from CUHK. I come from the Institute of automation of the Chinese Academy of Sciences. My WeChat is 971173235. Can you discuss it with...

@lizifan123 该[链接](https://drive.google.com/file/d/1ad4lxks68vngs_pCaqs9w_L-fGvtR7nQ/view)为swin_tiny pytorch1.4的预训练模型 (google driver)。

In the previous vesion of mmdetection (v1.x), the background class is included in the config file, i.e, "num_classes=15+1".

@Chenanxinyi (1) Loss_rbox is designed for points learning as the main term, loss_spatial is designed for the outlier point as the penalty item. (2) This is coase-to-fine framwork, the refine...

@runever 参考此[代码](https://github.com/LiWentomng/OrientedRepPoints/blob/main/DOTA_devkit/prepare_dota1_ms.py)对dota进行处理。

@runever 你好 不需要自己手动剔除， 本身mmdetection框架下对应的data pipeline 有filter 的操作，过滤掉没有标注的图片，本代码也有过滤掉特别小尺寸的目标的操作。

@Hxyou Hi, great work. Would you like to release the checkpoint files soon? I can't wait to try it~

@unmo @crazycth Hello, any update? I also encounter this problem.

@hawk2333 多谢！ 已在该仓库主页 添加此链接，帮助读者更快配置环境。