We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
作者您好,先介绍一下我的实验情况:我用下载的权重文件和自己训练的权重分别进行推理,mAP分别是27.1和23.8,这导致最终oriented rcnn检测DOTA测试集结果差距较大。下载的权重文件最终得到的结果与论文数据33.31基本一致,而我自己训练的权重最终测试集mAP只有28.15。 所以想请教一下,DOTA数据集在裁剪清洗阶段您是怎样操作的?是否裁剪策略不同会影响训练效果?
The text was updated successfully, but these errors were encountered:
你好,裁切脚本是使用mmrotate的默认裁切方法(https://github.com/open-mmlab/mmrotate/blob/main/tools/data/dota/README.md),我目前没有试过其他裁剪策略。另外在issue中已经上传了DOTA数据集的伪标签(https://github.com/Luo-Z13/pointobb/issues/17#issuecomment-2343354974),其中的true_rbox字段是对应的裁切后的原始真值rbox,可以与你自己的裁切结果进行查看核对。
Sorry, something went wrong.
No branches or pull requests
作者您好,先介绍一下我的实验情况:我用下载的权重文件和自己训练的权重分别进行推理,mAP分别是27.1和23.8,这导致最终oriented rcnn检测DOTA测试集结果差距较大。下载的权重文件最终得到的结果与论文数据33.31基本一致,而我自己训练的权重最终测试集mAP只有28.15。
所以想请教一下,DOTA数据集在裁剪清洗阶段您是怎样操作的?是否裁剪策略不同会影响训练效果?
The text was updated successfully, but these errors were encountered: