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 ability to call specific post processing algorithms after reverse one-hot encoding #494

Merged
merged 22 commits into from
Sep 12, 2022

Conversation

sarthakpati
Copy link
Collaborator

@sarthakpati sarthakpati commented Sep 11, 2022

Fixes #493

Proposed Changes

  • new key added for params that controls when the post-processing algorithm is applied
  • ensuring post processing is applied in 2 different ways during the forward pass
  • updated default model output for segmentation
  • added a helper function for tests to get temp config file path
  • added docs

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
  • History 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 [1,2,3,4]

@sarthakpati sarthakpati marked this pull request as draft September 11, 2022 16:46
@codecov
Copy link

codecov bot commented Sep 12, 2022

Codecov Report

Merging #494 (08cca1a) into master (be60609) will increase coverage by 0.11%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master     #494      +/-   ##
==========================================
+ Coverage   93.18%   93.30%   +0.11%     
==========================================
  Files         104      104              
  Lines        6458     6468      +10     
==========================================
+ Hits         6018     6035      +17     
+ Misses        440      433       -7     
Flag Coverage Δ
unittests 93.30% <100.00%> (+0.11%) ⬆️

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

Impacted Files Coverage Δ
GANDLF/compute/forward_pass.py 93.39% <100.00%> (+1.28%) ⬆️
GANDLF/data/post_process/__init__.py 100.00% <100.00%> (ø)
GANDLF/data/post_process/tensor.py 100.00% <100.00%> (ø)
GANDLF/parseConfig.py 77.32% <100.00%> (+0.57%) ⬆️
GANDLF/utils/tensor.py 88.27% <100.00%> (ø)
testing/test_full.py 98.97% <100.00%> (+0.31%) ⬆️

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

@sarthakpati sarthakpati merged commit 3d00791 into mlcommons:master Sep 12, 2022
@sarthakpati sarthakpati deleted the 493_specialized_post_process branch September 12, 2022 23:26
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.

Allow post_processing to happen either before or after reverse_one_hot_encoding
2 participants