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

Some updates to optical flow datasets #5004

Merged
merged 2 commits into from
Dec 8, 2021
Merged

Some updates to optical flow datasets #5004

merged 2 commits into from
Dec 8, 2021

Conversation

NicolasHug
Copy link
Member

@NicolasHug NicolasHug commented Nov 29, 2021 •
edited by pytorch-probot bot
Loading

This PR does a few different things related to the optical flow datasets:

  • always return an RGB image, like for the rest of the datasets (there are some images that come in RGBA or Grayscale but the transforms don't support these, so we need to convert)
  • rename valid in to valid_flow_mask which is clearer
  • allow the transforms to generate the valid_flow_mask from the flow values. This helps keeping the reference code clean.
  • A few doc clarifications
  • Implement __rmul__ which helps duplicating a dataset like 100 * sintel. Might remove eventually, it will depend on the training reference eventually

cc @pmeier

@facebook-github-bot
Copy link

facebook-github-bot commented Nov 29, 2021 •
edited
Loading

💊 CI failures summary and remediations

As of commit aabcd21 (more details on the Dr. CI page):

💚 💚 Looks good so far! There are no failures yet. 💚 💚

This comment was automatically generated by Dr. CI (expand for details).

Please report bugs/suggestions to the (internal) Dr. CI Users group.

Click here to manually regenerate this comment.

@NicolasHug NicolasHug mentioned this pull request Dec 3, 2021
Merged
datumbox
datumbox approved these changes Dec 7, 2021
View reviewed changes
Copy link
Contributor

@datumbox datumbox left a comment

Choose a reason for hiding this comment

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

Stamp

@NicolasHug NicolasHug merged commit a57e45c into pytorch:main Dec 8, 2021
@NicolasHug NicolasHug added module: datasets other if you have no clue or if you will manually handle the PR in the release notes labels Dec 8, 2021
facebook-github-bot pushed a commit that referenced this pull request Dec 9, 2021
@facebook-github-bot
[fbsync] Some updates to optical flow datasets (#5004)
683167f 
Reviewed By: NicolasHug

Differential Revision: D32950932

fbshipit-source-id: a775ede624bf71cf8716f276892831717e55a4f7
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@datumbox datumbox datumbox approved these changes

Assignees
No one assigned
Labels
ciflow/default cla signed module: datasets other if you have no clue or if you will manually handle the PR in the release notes
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@NicolasHug @facebook-github-bot @datumbox