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

我使用和您相同的数据集以及参数训练,channel prun的结果相仿,但是layer prun后的map在微调前只有20,可能是什么问题呢? #14

Open
px2017 opened this issue Dec 6, 2019 · 2 comments

Comments

@px2017
Copy link

px2017 commented Dec 6, 2019

No description provided.

@zbyuan
Copy link
Collaborator

zbyuan commented Dec 6, 2019

@px2017
hi In the course of our experiments, the layer_prune has a great impact on mAP

@tanluren
Copy link
Owner

tanluren commented Dec 6, 2019

你好,刚更新了剪层策略,你可以试试新策略的效果。剪层对于精度的损害的确较大,但是提速明显。精度可以通过微调回升,不同的剪层数也会有不同的效果。另外影响最大的是稀疏训练,稀疏压缩的好,精度也能保持的高。

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