A tiny Python library to create and train feedforward neural networks

library, machine-learning, neural-network, python
pip install nnweaver==0.2



Coverage Status Build Status

NNWeaver is a tiny Python library to create and train feedforward neural networks. We developed this library as a project for a Machine Learning course.

Some of its features are:

  1. Simple API, easy to learn.
  2. Validation functions included.
  3. Lightweight and with few dependencies.
  4. Live loss/epoch curve display.


You can install NNWeaver from the GitHub source with the following commands:

git clone https://github.com/gvinciguerra/nnweaver.git
cd nnweaver
python3 setup.py install

You can also run the test suite with python3 setup.py test.

Getting started

Specify a Neural Network Topology

You can create a feedforward neural network specifying the number of inputs as the argument of NN, and the number of outputs by adding a Layer:

from nnweaver import *
nn = NN(3)
nn.add_layer(Layer(5, Linear))

You can always add more layers, specify an activation function and a weights initializer, as the following lines of code show:

nn.add_layer(Layer(7, Sigmoid))
nn.add_layer(Layer(6, Rectifier, uniform(0, 0.05)))
nn.add_layer(Layer(42, TanH, glorot_uniform()))

See activations for the list of available activation functions.

Train the Neural Network

Now, choose a Loss function, pass it to an Optimizer (like the stochastic gradient descent) and start the training:

sgd = SGD(MSE)
sgd.train(nn, x, y, learning_rate=0.3)

There are other arguments to pass to the SGD.train() method, for example:

sgd.train(nn, x_train, y_train,
          learning_rate_time_based(0.25, 0.001),
          batch_size=10, epochs=100, momentum=0.85)

Also, you may want to control the model complexity. SGD.train() has a regularizer argument, that accepts an instance of the L1L2Regularizer class.

A very, very simple example


For more information, tutorials, and API reference, please visit NNweaver's online documentation or build your own offline copy executing python3 setup.py docs.


This project is licensed under the terms of the MIT License.