模型量化成int8之后的尺寸问题 #4554
ZhenyuYangGithub
started this conversation in
General
Replies: 1 comment 2 replies
-
你要看看你模型里都有些什么 OP. ncnn 支持对特定的 OP, 如 Linear 和 Conv 等做 int8 量化。 如果你的模型里,只有很少的 OP 支持量化,那么你看不到 4:1 的关系. |
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
我的模型量化成int8之后,模型.bin文件的尺寸变成了原来文件的1/2。但理论上讲,fp32的模型量化成int8,应该是4:1的尺寸关系。请问这是什么原因?
Beta Was this translation helpful? Give feedback.
All reactions