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

Make Dropout docstring clear w.r.t. N-D dropout #1490

Merged
merged 4 commits into from
Jan 31, 2021

Conversation

darsnack
Copy link
Member

@darsnack darsnack commented Jan 30, 2021

Make the docstring specify N-dimensional dropouts more clearly (i.e. so that people don't think we don't have Dropout3d etc.).

PR Checklist

  • Tests are added
  • Entry in NEWS.md
  • Documentation, if applicable
  • Final review from @dhairyagandhi96 (for API changes).

@darsnack darsnack mentioned this pull request Jan 30, 2021
92 tasks
src/layers/normalise.jl Outdated Show resolved Hide resolved
Co-authored-by: Brian Chen <ToucheSir@users.noreply.github.com>
@ToucheSir
Copy link
Member

Alternative to the suggested edit which avoids the e.g. + i.e. combo:

To apply dropout along certain dimension(s), specify the `dims` keyword.
e.g. `Dropout(p; dims = 3)` will randomly zero out entire channels on WHCN input (also called 2D dropout).

Copy link
Member

@DhairyaLGandhi DhairyaLGandhi left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

bors r+

@bors
Copy link
Contributor

bors bot commented Jan 31, 2021

Build succeeded:

@bors bors bot merged commit 8f7ef92 into FluxML:master Jan 31, 2021
@darsnack darsnack deleted the darsnack/dropout-doc branch February 1, 2021 16:01
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