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.

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

CPU version of smooth L1 loss layer implemented based #12

Open
wants to merge 1 commit into
base: fast-rcnn
Choose a base branch
from

Conversation

patricio-astudillo
Copy link

CPU version of smooth L1 loss layer implemented based on the GPU version. Peer review requested.

@saiprabhakar
Copy link

@patricio-astudillo @rbgirshick I implemented the code based on GPU code of smooth l1 loss, but the gpu code doesnt take weights into consideration in its back propagation. And the back propagation in this CPU implementation includes it.
Is this a mistake or am I missing something?

@Lukeeeeee
Copy link

How to use the CPU layer of SmoothL1Loss Layer? Just copy your code to the original one?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants