/ModelSoups

ModelSoups for Tensorflow2 and Torch

Primary LanguageJupyter NotebookMIT LicenseMIT

Model Soups

This is an implementation of "Model Soups" on Keras, Tensorflow and Torch.

The implementation is based on paper[1].

Method

  • Uniform Soup
  • Greedy Soup

Requirements

  • Python 3
  • Tensorflow2 or Torch

Reference

  1. Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time, Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S. Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, Ludwig Schmidt, https://arxiv.org/abs/2203.05482v1

Contributor