Metadata-Version: 2.3
Name: scor
Version: 0.1.1
Summary: The library for ICANN 2025 Paper 'Stochastic Covariance Regularization for Imbalanced Datasets'
License: MIT
Author: Ahmet Erdem
Author-email: erdemah22@itu.edu.tr
Requires-Python: >=3.10
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Dist: numpy (>=1.23)
Requires-Dist: scikit-learn (>=1.1)
Requires-Dist: torch (>=2.1.0)
Requires-Dist: torchvision (>=0.16.0)
Requires-Dist: tqdm (>=4.64)
Description-Content-Type: text/markdown

# Stochastic Covariance Regularization

## imagenet.py

This file is for training models with various loss functions on the ImageNet dataset.
Code from [here](https://github.com/pytorch/examples/tree/main/imagenet) is adapted 
to be used with loss functions defined in this repository.

A "loss" option is included to the adapted code. Run ```python imagenet.py --help```
for a proper description.

