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.

Sign up for GitHub

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

Jump to bottom

Develop a fake dequantized op for fixed-point quantization training framework. #10965

Merged
merged 4 commits into from
May 30, 2018
Merged

Develop a fake dequantized op for fixed-point quantization training framework. #10965

merged 4 commits into from
May 30, 2018

Conversation

qingqing01
Copy link
Contributor

@qingqing01 qingqing01 commented May 28, 2018 •
edited
Loading

Fix #10964

Another op fake_quantize_op will be added later. Although fake_dequantize_op can be replaced by elementwise_mul and elementwise_div, for the sake of symmetry, we implement this by C++ op.

@qingqing01 qingqing01 mentioned this pull request May 28, 2018
Closed
6 tasks
panyx0718
panyx0718 previously approved these changes May 29, 2018
View reviewed changes
Copy link
Contributor

@panyx0718 panyx0718 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also add a test?

@qingqing01
Copy link
Contributor Author

@panyx0718 Thanks! Forgot git add the test file before.

@qingqing01 qingqing01 merged commit 3a29821 into PaddlePaddle:develop May 30, 2018
@qingqing01 qingqing01 deleted the fake_dequant_op branch November 14, 2019 05:26
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@panyx0718 panyx0718 panyx0718 approved these changes

@kuke kuke Awaiting requested review from kuke

@wanghaoshuang wanghaoshuang Awaiting requested review from wanghaoshuang

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
2 participants
@qingqing01 @panyx0718