Skip to content

Added option to bias the patch extraction for label sampler #771

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
sarthakpati merged 21 commits into from
Jan 18, 2024
Merged

Added option to bias the patch extraction for label sampler #771

sarthakpati merged 21 commits into from
Jan 18, 2024

Conversation

@scap3yvt
Copy link
Collaborator

@scap3yvt scap3yvt commented Jan 12, 2024 •
edited by sarthakpati
Loading

Fixes #767

Proposed Changes

  • "patch_sampler" key in config is now a dict, where multiple options can be passed in (such as "enable_padding", "padding_mode", and so on)
  • parseConfig updated to include defaults for patch_sampler
  • added option to ensure class_weights are used to bias the label sampler

Checklist

  • I have read the CONTRIBUTING guide.
  • My PR is based from the current GaNDLF master .
  • Non-breaking change (does not break existing functionality): provide as many details as possible for any breaking change.
  • Function/class source code documentation added/updated.
  • Code has been blacked for style consistency.
  • If applicable, version information has been updated in GANDLF/version.py.
  • If adding a git submodule, add to list of exceptions for black styling in pyproject.toml file.
  • Usage documentation has been updated, if appropriate.
  • Tests added or modified to cover the changes; if coverage is reduced, please give explanation.
  • If customized dependency installation is required (i.e., a separate pip install step is needed for PR to be functional), please ensure it is reflected in all the files that control the CI, namely: python-test.yml, and all docker files [1,2,3].

@scap3yvt scap3yvt marked this pull request as draft January 12, 2024 20:38
@github-actions
Copy link
Contributor

github-actions bot commented Jan 12, 2024 •
edited
Loading

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

@codecov
Copy link

codecov bot commented Jan 15, 2024 •
edited
Loading

Codecov Report

Attention: 7 lines in your changes are missing coverage. Please review.

Comparison is base (ddf8fb9) 94.70% compared to head (cb41903) 94.68%.

❗ Current head cb41903 differs from pull request most recent head ad9709b. Consider uploading reports for the commit ad9709b to get more accurate results

Files Patch % Lines
GANDLF/data/ImagesFromDataFrame.py 53.33% 7 Missing ⚠️
Additional details and impacted files 
@@            Coverage Diff             @@
##           master     #771      +/-   ##
==========================================
- Coverage   94.70%   94.68%   -0.03%     
==========================================
  Files         117      117              
  Lines        8240     8252      +12     
==========================================
+ Hits         7804     7813       +9     
- Misses        436      439       +3
Flag Coverage Δ
unittests 94.68% <74.07%> (-0.03%) ⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@sarthakpati
Copy link
Collaborator

sarthakpati commented Jan 16, 2024

Please update the tests to ensure new lines are covered before opening this PR for review.

@scap3yvt
Copy link
Collaborator Author

scap3yvt commented Jan 17, 2024

@sarthakpati - the OpenFL tests seem to be broken, and need a separate PR (in addition to #772).

@sarthakpati sarthakpati mentioned this pull request Jan 17, 2024
Closed
@scap3yvt scap3yvt marked this pull request as ready for review January 18, 2024 18:04
@scap3yvt
Copy link
Collaborator Author

scap3yvt commented Jan 18, 2024

This is ready for review, but I am unsure how to proceed WRT the failing OpenFL tests.

@sarthakpati sarthakpati changed the title 767 add option to bias the patch extraction for label sampler -- DRAFT! 767 add option to bias the patch extraction for label sampler Jan 18, 2024
@sarthakpati sarthakpati changed the title 767 add option to bias the patch extraction for label sampler Added option to bias the patch extraction for label sampler Jan 18, 2024
sarthakpati
sarthakpati approved these changes Jan 18, 2024
View reviewed changes
Copy link
Collaborator

@sarthakpati sarthakpati left a comment

Choose a reason for hiding this comment

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

LGTM

@sarthakpati sarthakpati merged commit c666e09 into mlcommons:master Jan 18, 2024
@github-actions github-actions bot locked and limited conversation to collaborators Jan 18, 2024
@scap3yvt scap3yvt deleted the 767-add-option-to-bias-the-patch-extraction-for-label-sampler branch January 18, 2024 18:37
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Reviewers

@sarthakpati sarthakpati sarthakpati approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

Add option to bias the patch extraction for label sampler

2 participants

@scap3yvt @sarthakpati