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

half-precision #5

Closed
pedropgusmao opened this issue Jun 16, 2017 · 2 comments
Closed

half-precision #5

pedropgusmao opened this issue Jun 16, 2017 · 2 comments

Comments

@pedropgusmao
Copy link

Is it possible to convert a pre-trained ENet into a half-precision version?
Thanks
@TimoSaemann
Copy link
Owner

This question is independent of ENet but rather a general question. Did you ask this on caffe-users as well?
I think in general this should be possible. However, this does not speed up the network, because caffe-enet does not support fp16 operations.
The Caffe framework from Nvidia supports fp16 operations: https://github.com/NVIDIA/caffe
If you like to use ENet with fp16, you have to make all necessary modifications to the NVIDIA/caffe, which were done at caffe-enet.

@pedropgusmao
Copy link
Author

Thanks

@guantinglin guantinglin mentioned this issue Dec 3, 2017
Open
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
Development

No branches or pull requests
2 participants
@pedropgusmao @TimoSaemann