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

模型·大小对比 #99

Open
dan123yi opened this issue Dec 2, 2021 · 8 comments
Open

模型·大小对比 #99

dan123yi opened this issue Dec 2, 2021 · 8 comments

Comments

@dan123yi
Copy link

dan123yi commented Dec 2, 2021

请问作者的模型大小对比图怎么得到的,我每次改变量化bit后保存的模型大小都一样

@YangNuoCheng
Copy link

我也有同样的问题,比如我们使用4bit的量化,量化结果是16个,但它们的值还保持浮点数形式,这样真的可以压缩模型的大小吗?

@dan123yi
Copy link
Author

dan123yi commented Dec 17, 2021 via email

@dan123yi
Copy link
Author

dan123yi commented Dec 17, 2021 via email

@YangNuoCheng
Copy link

这个op级是什么意思呀,意思是使用tensorrt做加速的时候可以自动的把模型量化到对应的整数吗?
量化新手,感谢回复!

@dan123yi
Copy link
Author

dan123yi commented Dec 17, 2021 via email

@666DZY666
Copy link
Owner

这个仓库是做量化训练的,模型都是浮点表示的。给出的数据里模型大小是自己理论计算的,这个计算可以搞成代码,大家可以写写加进来。

@rourou8023
Copy link

@dan123yi 您好,麻烦问下,量化后的模型,应该怎么处理呢?我二值化训练之后的模型依然是浮点型的,怎么修改为二值呢?

@dan123yi
Copy link
Author

我也想问:sob::sob::sob:

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

4 participants