-
Notifications
You must be signed in to change notification settings - Fork 18
New issue
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
DOTA_TASK1验证问题 #10
Comments
训练完的权重模型文件可通过publish_model.py删除部分无用的参数来减小所占内存 |
请问一下不删除会影响网络模型的精度吗? |
主要问题是最后上传到官网的Task_merged.zip文件40MB 预测的框要比官网模型权重跑出来的很多。这多少会影响精度吧,我确实是按照文档跑下来的,真的不知道哪里出问题了。 |
你拿readme提供的模型测试一下精度不就清楚了吗,测试没问题但自己跑出来的模型精度有问题,那就要考虑一下配置文件的相关参数是不是和作者提供的不一致 |
好的 我再检查检查 多谢 麻烦了 |
你好,我通过该项目swin-t跑出来的权重文件latest.pth在dotav1测试集上进行测试得到的Task_merged.zip文件足足有40M,result.pkl600M,上传到官网测试的精度也不正常。
我尝试从https://github.com/LiWentomng/OrientedRepPoints下载了权重文件,然后加载到你的项目中测试Task_merged.zip为5M,result.pkl16M,精度是原论文的精度。
我不知道我复现哪里出了问题了,我想请问一下您的测试权重和文件是怎么样的?
The text was updated successfully, but these errors were encountered: