项目作者: harveyslash

项目描述 :
Automatic differentiation in python
高级语言: Python
项目地址: git://github.com/harveyslash/sympyle.git
创建时间: 2018-06-13T18:25:30Z
项目社区:https://github.com/harveyslash/sympyle

开源协议:GNU General Public License v3.0

下载


Sympyle

Simple Symbolic Graphs in Python

Build Status
codecov
CodeFactor

About

Project documentation: http://harveyslash.github.io/sympyle/

Sympyle is a Python library to demonstrate the inner workings of Computational
Graphs. Computational Graphs are used by highly optimised computational
frameworks like tensorflow and
pytorch.

However, these frameworks make several assumptions and optimisations in order
to optimise for speed and memory. This often makes it harder to understand
the inner workings of how these libraries work.

Sympyle is a simplified model library to demonstrate the working of
computational graphs, and how
backpropagation
works on arbitrary ‘networks’.

Examples and tutorials

All tutorials are under docs/source/tutorials and interactible at https://harveyslash.github.io/sympyle/ (under the tutorials section)