-
Notifications
You must be signed in to change notification settings - Fork 11
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
你好。我训练COCO数据集,发现先关键点loss居高不下 #3
Comments
可以发下你的config和log吗,可能是lr的问题 |
您好,我发现COCO数据集收敛了。但是我自己用labelme标注了2张图片,其中有人的bounding box和3个keypoints 但是不收敛,好难过,方便吗,大佬,加一下qq |
大佬,我QQ是370308707 |
我跟你正相反,loss几乎为0,但是评估的时候AP也为0 |
因为我使用一个rtx4070训练的,所以lr应该改成0.0025吗 |
检查data, 降低lr等 |
嗯嗯,目前使用lr=0.0025 |
不过我使用pretrained_weights 训练,loss基本没有变,一直是3左右 |
你好,我用您的代码训练COCOC数据集,发现'loss_classifier'会下降,但是 'loss_keypoint'基本居高不下
The text was updated successfully, but these errors were encountered: