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
offect loss、 score_loss 模型训练开始loss出现先升后降,但是下降过程中震荡也比较大,几乎没有下降趋势,请问是loss设置权重问题吗?有什么推荐的权重设置?
The text was updated successfully, but these errors were encountered:
Hi,
我都是参照原作的参数设置, 我自己尝试过调节权重, 效果不明显, 有兴趣的话你可以自己实验一下.
另外offset loss确实下降趋势不明显, 有可能是训练样本的offset gt太少 (只有最近点的offset), 但是原作又明确训练ground truth为最近target candidate的offset. 所以这部分我也比较疑惑.
socre loss 总体呈下降趋势, 我认为没有太大问题.
Best Regards, Jianbang
Sorry, something went wrong.
Hi,我的情况是offset震荡下降;但是score收敛了,但只收敛了一点点。
No branches or pull requests
offect loss、 score_loss 模型训练开始loss出现先升后降,但是下降过程中震荡也比较大,几乎没有下降趋势,请问是loss设置权重问题吗?有什么推荐的权重设置?
The text was updated successfully, but these errors were encountered: