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

请问为何微调之后保存的模型大小变大了 #68

Open
wayne2tech opened this issue May 28, 2021 · 4 comments
Open

请问为何微调之后保存的模型大小变大了 #68

wayne2tech opened this issue May 28, 2021 · 4 comments

Comments

@wayne2tech
Copy link

您好,首先感谢您的工作
如题,我打印出来了剪枝之后的模型参数和微调之后的模型参数,发现微调之后模型的channel又恢复到了原模型每个卷积层的channel,所以微调之后保存的模型就变大了,不知道是我的操作问题还是代码就是这个样子的呢

@Eric-mingjie
Copy link
Owner

如果你用的是mask implementation的话是有可能变大,因为我们加了新的channel selection layer。

@wayne2tech
Copy link
Author

感谢您的答疑,我大概了解了您的思路,我还有一个疑问:
我finetune之后的参数量是比剪枝之后的参数量大的(resnet剪枝)(我的参数量大概从400k->500k+),但是从您的实验结果来看,您对resnet剪枝和finetune之后的参数量是一样的,请问这是为什么呢?

@Eric-mingjie
Copy link
Owner

finetune不会改变参数量,都是同一个结构

@YHLymj
Copy link

YHLymj commented May 24, 2022

您好!请问关于微调后模型大小变大的问题您是如何解决的呢?
期待您的回复

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