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
你好
我这边可视化了开源的BiRefNet-matting-epoch_100.pth和BiRefNet-portrait-epoch_150.pth两个抠图模型对梯度预测的结果图
结果如下: BiRefNet-matting-epoch_100.pth:
BiRefNet-portrait-epoch_150.pth:    
结果包含了对训练集中两张图片的梯度预测和梯度gt,我发现对图像梯度的学习效果并不理想
并且我在训练时也发现梯度学习的loss早期之后就几乎没有下降
以上的实验均是在matting的设置下进行的
因此,我有点怀疑外部监督(梯度的监督)的作用是否足够,我的感受是挺有限的
The text was updated successfully, but these errors were encountered:
我其实也感觉比较有限😂, 特别是在大规模的使用场景训练下. 说实话这种辅助task的影响是不会很直接的, 可以后续加重它的权重看看.
Sorry, something went wrong.
No branches or pull requests
你好
我这边可视化了开源的BiRefNet-matting-epoch_100.pth和BiRefNet-portrait-epoch_150.pth两个抠图模型对梯度预测的结果图
结果如下:




BiRefNet-matting-epoch_100.pth:
结果包含了对训练集中两张图片的梯度预测和梯度gt,我发现对图像梯度的学习效果并不理想
并且我在训练时也发现梯度学习的loss早期之后就几乎没有下降
以上的实验均是在matting的设置下进行的
因此,我有点怀疑外部监督(梯度的监督)的作用是否足够,我的感受是挺有限的
The text was updated successfully, but these errors were encountered: