https://github.com/tensorflow/kfac

An implementation of KFAC for TensorFlow
https://github.com/tensorflow/kfac

Last synced: 7 months ago
JSON representation

An implementation of KFAC for TensorFlow

• Host: GitHub
• URL: https://github.com/tensorflow/kfac
• Owner: tensorflow
• License: apache-2.0
• Created: 2018-02-01T23:14:00.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2022-02-11T20:34:05.000Z (over 3 years ago)
• Last Synced: 2025-03-29T01:08:01.567Z (7 months ago)
• Language: Python
• Size: 1.73 MB
• Stars: 198
• Watchers: 17
• Forks: 41
• Open Issues: 9
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# K-FAC: Kronecker-Factored Approximate Curvature

[![Travis](https://img.shields.io/travis/tensorflow/kfac.svg)](https://travis-ci.org/tensorflow/kfac)

**K-FAC in TensorFlow** is an implementation of [K-FAC][kfac-paper], an

approximate second-order optimization method, in TensorFlow.

[kfac-paper]: https://arxiv.org/abs/1503.05671

## Installation

`kfac` is compatible with Python 2 and 3 and can be installed directly via

`pip`,

```shell

# Assumes tensorflow or tensorflow-gpu installed

$ pip install kfac

# Installs with tensorflow-gpu requirement

$ pip install 'kfac[tensorflow_gpu]'

# Installs with tensorflow (cpu) requirement

$ pip install 'kfac[tensorflow]'

```

## KFAC DOCS

Please check [KFAC docs][kfac_docs] for a detailed description with examples

of how to use KFAC. Check the [Keras KFAC docs][keras_docs] for information on

using KFAC with Keras.

[kfac_docs]: https://github.com/tensorflow/kfac/tree/master/docs/index.md

[keras_docs]: https://github.com/tensorflow/kfac/tree/master/kfac/python/keras/README.md