-
Notifications
You must be signed in to change notification settings - Fork 5.7k
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
fix clip extra when QAT export model #38323
Conversation
Thanks for your contribution! |
@@ -173,7 +173,7 @@ def build_program(main, startup, is_test): | |||
'quant_scale_model' + dev_name, ['image', 'label'], [loss], | |||
exe, | |||
server_program, | |||
clip_extra=True) | |||
clip_extra=False) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
单测可以不改吗?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
done
@@ -145,7 +145,7 @@ def build_program(main, startup, is_test): | |||
'./infer_model', ['image', 'label'], [loss], | |||
exe, | |||
test_program, | |||
clip_extra=True) | |||
clip_extra=False) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
单测可以不改吗
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
done
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
PR types
Bug fixes
PR changes
APIs
Describe
When export model in QAT,
clip_extra=True
, which may cause some quantitative model fail to run normally on Paddle Lite. So resetclip_extra=False
.