Metadata-Version: 2.1
Name: nnfpy
Version: 1.1.0
Summary: Neural network for python
Home-page: https://github.com/sopho-s/nnfpy
Author: Nick Woods, Olivier Hinds
Author-email: woodsnicholas01@gmail.com
License: MIT
Platform: UNKNOWN
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Description-Content-Type: text/markdown
License-File: LICENSE.txt

# **NNFPY**

Welcome to a project I have been working on for a while and have decided to make this a public package.

This package is used to create neural networks with 'ease'.

It compresses a whole neural network down to this:

```
net = onednet.create([denselayer("relu", 2, 64), denselayer("relu", 64, 2), endlayer("softmax"), timesloss(0.00001)])

data = net.runnet(0.1, 50000, X, y, storedata(), momentum=momentum(0.5), printevery=1000, batchsize=100)

outs = net.predwithout(X, y)
```

Just to basically describe what has happened in these lines of code:

The first line has created a network with one input layer taking two input values a hidden layer of 64 neurons and an output layer of 2 output

The second line has run the network a 50000 times

The third line shows the predictions and the average cost

## **Installing**

To install excecute the following command

>pip install nnfpy


