Skip to content

/ models

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

Jump to bottom

PyramidBox face_detection: is it possible to transpile to float16? #1924

Open
colojaro opened this issue Mar 27, 2019 · 1 comment
Open

PyramidBox face_detection: is it possible to transpile to float16? #1924

colojaro opened this issue Mar 27, 2019 · 1 comment

Comments

@colojaro
Copy link

@colojaro colojaro commented Mar 27, 2019

I have seen multiple references in PaddlePaddle code to transpiling to float16 with gains on Volta GPUs. This out of date doc gives instructions but I can't find anything for recent versions:
http://www.paddlepaddle.org/documentation/docs/en/1.3/design/data_type/float16.html

I don't know Chinese but it seems as though the feature has been removed or moved. Is it possible to convert the face detector and will it be faster?
@qingqing01
Copy link
Collaborator

@qingqing01 qingqing01 commented Mar 27, 2019

We add example for image classfication on ImageNet, see: https://github.com/PaddlePaddle/models/tree/develop/fluid/PaddleCV/image_classification/#using-mixed-precision-training .

But, we haven't experimented on PyramidBox. We have plans to do F16 for detection in the future.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Linked pull requests

Successfully merging a pull request may close this issue.

None yet
2 participants
@qingqing01 @colojaro
You can’t perform that action at this time.