Quick search


version 0.7

Deep neural networks without the learning cliff! A wrapper library compatible with scikit-learn.





Deep neural network implementation without the learning cliff! This library implements multi-layer perceptrons as a wrapper for the powerful ``Lasagne`` library that\'s compatible with ``scikit-learn`` for a more user-friendly and Pythonic interface.

**NOTE**: This project is possible thanks to the ` Conference <>`_ on **July 18-20**. Join us in **Vienna**!

|Documentation Status| |Code Coverage| |License Type| |Project Stars|



Thanks to the underlying ``Lasagne`` implementation, this library supports the following neural network features, which are exposed in an intuitive and `well documented <>`_ API:

* **Activation Functions \u2014**
* Nonlinear: ``Sigmoid``, ``Tanh``, ``Rectifier``.
* Linear: ``Linear``, ``Gaussian``, ``Softmax``.
* **Layer Types \u2014** ``Convolution`` (greyscale and color, 2D), ``Dense`` (standard, 1D).
* **Learning Rules \u2014** ``sgd``, ``momentum``, ``nesterov``, ``adadelta``, ``adagrad``, ``rmsprop``.
* **Regularization \u2014** ``L1``, ``L2`` and ``dropout``.
* **Dataset Formats \u2014** ``numpy.ndarray``, ``scipy.sparse``, coming soon: iterators.

If a feature you need is missing, consider opening a `GitHub Issue <>`_ with a detailed explanation about the use case and we\'ll see what we can do.


To download and setup the latest official release, you can do so from PYPI directly::

> pip install scikit-neuralnetwork

This will install a copy of `Lasagne` too as a dependency. We recommend you use a virtual environment for Python.

Then, you can run the tests using ``nosetests -v sknn``, and other samples or benchmarks are available in the ``examples/`` folder.

Getting Started

The library supports both regressors (to estimate continuous outputs from inputs) and classifiers (to predict labels from features). This is the ``sklearn``-compatible API:

.. code:: python

from sknn.mlp import Classifier, Layer

nn = Classifier(
Layer(\"Rectifier\", units=100),
n_iter=10), y_train)

y_valid = nn.predict(X_valid)

score = nn.score(X_test, y_test)

The `generated documentation <>`_ as a standalone page where you can find more information about parameters, as well as examples in the `User Guide <>`_.


|Documentation Status| |Code Coverage| |License Type| |Project Stars|

.. |Documentation Status| image::

.. |Code Coverage| image::

.. |License Type| image::

.. |Project Stars| image::



You can download the latest distribution from PyPI here:

Using pip

You can install scikit-neuralnetwork for yourself from the terminal by running:

pip install --user scikit-neuralnetwork

If you want to install it for all users on your machine, do:

pip install scikit-neuralnetwork
On Linux, do sudo pip install scikit-neuralnetwork.

If you don't yet have the pip tool, you can get it following these instructions.

This package was discovered in PyPI.