search

pytorch / torcheval

A library that contains a rich collection of performant PyTorch model metrics, a simple interface to create new metrics, a toolkit to facilitate metric computation in distributed training and tools for PyTorch model evaluations.
https://pytorch.org/torcheval
Other
215 stars 47 forks source link

Functional Version of Multiclass Binned AUPRC Library #142

Closed williamhufb closed 1 year ago

williamhufb commented 1 year ago

Summary: We add the functional version of the Multiclass Binned AUPRC library.

Also make minor fixes to Binned AUROC docstrings

Reviewed By: bobakfb

Differential Revision: D44599455

facebook-github-bot commented 1 year ago

This pull request was exported from Phabricator. Differential Revision: D44599455

codecov[bot] commented 1 year ago

Codecov Report

Merging #142 (6e1798b) into main (5bc9912) will decrease coverage by 0.01%. The diff coverage is 95.41%.

@@            Coverage Diff             @@
##             main     #142      +/-   ##
==========================================
- Coverage   95.64%   95.64%   -0.01%     
==========================================
  Files         170      170              
  Lines        9210     9316     +106     
==========================================
+ Hits         8809     8910     +101     
- Misses        401      406       +5
Impacted Files Coverage Δ
.../metrics/functional/classification/binned_auroc.py 72.97% <ø> (ø)
...ics/functional/classification/test_binned_auprc.py 93.19% <92.75%> (-0.56%) :arrow_down:
.../metrics/functional/classification/binned_auprc.py 100.00% <100.00%> (ø)

:mega: We’re building smart automated test selection to slash your CI/CD build times. Learn more