-
Notifications
You must be signed in to change notification settings - Fork 5.6k
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
Make post training quant API support dataloader #38686
Make post training quant API support dataloader #38686
Conversation
Thanks for your contribution! |
@@ -303,7 +307,7 @@ def __init__(self, | |||
self._program = None | |||
self._feed_list = None | |||
self._fetch_list = None | |||
self._data_loader = None | |||
self._data_loader = data_loader |
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.
能否加一下assert isinstance的判断,保证data_loader只能是Python Generator或者Paddle.io.DataLoader?
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.
已经加入了对输入的检查,十分感谢提醒~
… make-post-train-quant-support-data-loader
PR types
New features
PR changes
APIs
Describe
This PR makes
PostTrainingQuantization
supportpaddle.io.DataLoader
orPython Generator
input, which would not be wrapped byset_batch_generator
orset_sample_generator
.