Skip to content
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

在自动压缩中,如何查看蒸馏时的模型本身损失? #1824

Open
Wst-sd opened this issue Dec 29, 2023 · 2 comments
Open

在自动压缩中,如何查看蒸馏时的模型本身损失? #1824

Wst-sd opened this issue Dec 29, 2023 · 2 comments
Assignees

Comments

@Wst-sd
Copy link

Wst-sd commented Dec 29, 2023

蒸馏过程中目前打印的信息“INFO: Total iter: 240, epoch: 0, batch: 240, loss: 2.9188854694366455 soft_label: 2.9188854694366455” 只有蒸馏损失,当alpha<1.0时,应该有蒸馏损失+模型自身损失,但是不知道查看接口。

@XGZhang11
Copy link
Collaborator

应该需要去代码里打印一下

@zzjjay
Copy link
Collaborator

zzjjay commented Feb 18, 2024

自动压缩中是通过原网络和压缩后的网络进行蒸馏训练来恢复模型精度的,因此训练过程中仅有蒸馏损失,是不包含模型自身损失的。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants