KEMBAR78
adaptive pooling supports only specifying size in certain dimension by blackyang · Pull Request #3127 · pytorch/pytorch · GitHub
Skip to content

adaptive pooling supports only specifying size in certain dimension #3127

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
Merged
merged 2 commits into from
Nov 1, 2017
Merged

adaptive pooling supports only specifying size in certain dimension #3127

merged 2 commits into from
Nov 1, 2017

Conversation

@blackyang
Copy link
Contributor

Adaptive pooling supports only specifying size in certain dimensions. For example, we can have:

x = Variable(torch.rand(1,3,10,10))
m = nn.AdaptiveMaxPool2d((5,None))
y=m(x)
y.size()  # torch.Size([1, 3, 5, 10])

This is useful for certain sequence related tasks

@blackyang
Copy link
Contributor Author

blackyang commented Oct 15, 2017 •
edited
Loading

Maybe I should also change docs accordingly if this is merged

@soumith soumith merged commit 3cb3474 into pytorch:master Nov 1, 2017
@soumith
Copy link
Member

soumith commented Nov 1, 2017

if you can, please send a PR to fix the docs. thank you!

@blackyang blackyang mentioned this pull request Nov 16, 2017
Merged
@blackyang
Copy link
Contributor Author

@soumith I created a PR #3746 to fix the docs. Do you think it's okay?

@soumith
Copy link
Member

soumith commented Nov 16, 2017

it looks great, thank you!

@ailzhang ailzhang mentioned this pull request Jun 18, 2018
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

open source

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@blackyang @soumith @ezyang