Simple Automatic Differentiation in Python
Simple Symbolic Graphs in Python
Project documentation: http://harveyslash.github.io/sympyle/
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 coming soon
For now , you can see tests/ folder for usage
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size sympyle-0.0.12-py3-none-any.whl (9.2 kB)||File type Wheel||Python version py3||Upload date||Hashes View hashes|