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

Added UpSampling module and associated tests. #1264

Merged
merged 1 commit into from
Jul 21, 2017

Conversation

mikepound
Copy link
Contributor

@mikepound mikepound commented Jul 21, 2017

From issue #1262, a more generic UpSampling module that provides a wrapper to the recently added volumetric upsampling code. Behaves similarly to the pytorch upsample class, in that it infers 2D or 3D upsampling based on the input size, and can operate in either nearest neighbor or linear mode.

  • This module is a little thematically different to the existing upsampling modules, in that it works on either spatial or volumetric depending on the input.
  • There is cunn testing code, but I didn't include it as this is an nn commit. I wasn't sure if I could push to two repos at once.

@soumith soumith merged commit 14cedef into torch:master Jul 21, 2017
@soumith
Copy link
Member

soumith commented Jul 21, 2017

thanks Mike!

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.

2 participants