Metadata-Version: 2.1
Name: craynn
Version: 0.1.0
Summary: Yet another neural network toolkit.
Home-page: https://github.com/craynn/craynn
Author: Maxim Borisyak and contributors.
Author-email: maximus.been@gmail.com
Maintainer: Maxim Borisyak
Maintainer-email: maximus.been@gmail.com
License: MIT
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Requires-Dist: tensorflow (>=2.0.0)
Requires-Dist: numpy (>=1.17.1)
Requires-Dist: matplotlib (>=3.0.2)
Requires-Dist: pydotplus (>=2.0.2)
Provides-Extra: test
Requires-Dist: pytest (>=4.0.0) ; extra == 'test'
Requires-Dist: scipy (>=1.3.0) ; extra == 'test'

# CRAYNN

Yet Another toolkit for Neural Network slightly flavoured by Ultra-High Energy Cosmic Rays. 

## Philosophy

- it is just a collection of helpers for constructing tensorflow graphs;
- don't force any features;
- keep it modular and orthogonal:
  - e.g. any change in optimizers should not have any effect on the layers module. 

## TODO

- def helpers;
- common layers;
- dense layers;
- batch norm layer;
- conv layers;
- initialization;
- optimizers;
- network helper class.

