Automatic differentiation in python
Simple Symbolic Graphs in Python
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’.
All tutorials are under docs/source/tutorials and interactible at https://harveyslash.github.io/sympyle/ (under the tutorials section)