Factual package intelligence from PyPI

proxy-losses 0.1.3 package intelligence

proxy-losses is a PyTorch library of differentiable proxy losses for ranking metrics — intended as drop-in replacements for cross-entropy when the real objective is Average Precision or recall at a specific operating point.

pip install proxy-losses

Current version
0.1.3
Python requirement
>=3.10
License
MIT
Distribution type
Pure Python wheel
Release files
2 (1 wheels, 1 source)
Download size
109.6 KiB
Release history
3 releases with files
Median release cadence
1 days

proxy-losses dependencies

PyPI declares 2 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. torch >=2.8.0

Compatibility and release files

proxy-losses publishes 1 wheel and 1 source archive for version 0.1.3. Wheel platform tags: any.

No version-specific Python classifiers are declared.

Metadata completeness

PyPI does not currently declare: project URL. PyDeps marks these fields as unknown instead of guessing values.

Release activity and sources

PyPI lists 3 releases with files. The first dated release is ; 3 releases fall within the 365 days preceding the latest dated release. The current release files were uploaded on . The preceding dated release was .

The project does not publish external project URLs in its PyPI metadata.