Metadata-Version: 2.1
Name: sinnn
Version: 0.0.1
Summary: Numpy powered neural network library
Home-page: https://github.com/sohaibimran7/sinnn
Author: Sohaib Imran
Author-email: sohaibimran7@gmail.com
License: MIT
Platform: UNKNOWN
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.6
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: numpy

# sinnn
 Sohiab Imran's Numpy Neural Network.\
 sinnn is a numpy powered low code neural network library. 


 Work in progress 🔨 .
 To do:
 1) Add Regularisation
 2) Add more Initialisers
 3) Add more Optimisers


# Installation

pip install sinnn

Requirements:
    Numpy

# Features
Support for a limited number of features is available as the library is still new.
Supported features are:\
Layers: Dense, ReLU\
Initialisers: Zeros, SmallRandom\
Losses: MSE, CrossEntropy\
Metrics: loss, accuracy \
Optimisers: SGD, Momentum, AdaGrad\
utils: sigmoid, softmax, one_hot, batches, save_model, load_model


# Examples
Please refer to the examples directory for example deep learning problems solved using sinnn.

