From d303bbde5b3eb2dc4fe66aac76133c99d99495f5 Mon Sep 17 00:00:00 2001 From: "Alex J. Champandard" Date: Tue, 17 Nov 2015 21:24:49 +0100 Subject: [PATCH] Updating build procedure and documentation. --- .travis.yml | 2 +- README.rst | 14 ++++++-------- docs/pypi.rst | 10 +++++----- setup.py | 5 ++--- 4 files changed, 14 insertions(+), 17 deletions(-) diff --git a/.travis.yml b/.travis.yml index 4a839e9..778f675 100644 --- a/.travis.yml +++ b/.travis.yml @@ -14,7 +14,7 @@ before_install: install: - conda create --yes -q -n pyenv python=$TRAVIS_PYTHON_VERSION pip numpy scipy cython matplotlib scikit-learn nose pyyaml - source activate pyenv - - pip install -q git+https://github.com/Theano/Theano.git@rel-0.7 + - pip install -q git+https://github.com/Theano/Theano.git@a85a44fc#egg=Theano==0.8-dev - pip install -q argparse coveralls lasagne script: diff --git a/README.rst b/README.rst index 51f358d..e1dce34 100644 --- a/README.rst +++ b/README.rst @@ -1,7 +1,7 @@ scikit-neuralnetwork ==================== -Deep neural network implementation without the learning cliff! This library implements multi-layer perceptrons, auto-encoders and (soon) recurrent neural networks with a stable Future Proof™ interface that's compatible with ``scikit-learn`` for a more user-friendly and Pythonic interface. It's a wrapper for powerful existing libraries such as ``pylearn2`` now, and soon ``keras`` or ``blocks``. +Deep neural network implementation without the learning cliff! This library implements multi-layer perceptrons, auto-encoders and (soon) recurrent neural networks with a stable Future Proof™ interface that's compatible with ``scikit-learn`` for a more user-friendly and Pythonic interface. It's a wrapper for powerful existing libraries such as ``lasagne`` now, and soon ``keras`` or ``blocks``. **NOTE**: This project is possible thanks to the `nucl.ai Conference `_ on **July 20-22**. Join us in **Vienna**! @@ -12,7 +12,7 @@ Deep neural network implementation without the learning cliff! This library imp Features -------- -Thanks to the underlying ``pylearn2`` implementation, this library supports the following neural network features, which are exposed in an intuitive and `well documented `_ API: +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 —** * Nonlinear: ``Sigmoid``, ``Tanh``, ``Rectifier``, ``Maxout``. @@ -35,15 +35,14 @@ If you want to use the latest official release, you can do so from PYPI directly > pip install scikit-neuralnetwork -This contains its own packaged version of ``pylearn2`` from the date of the release (and tag) but will use any globally installed version if available. +This will install a copy of `Lasagne` too as a dependency. We recommend you use a virtual environment for Python. B) Pulling Repositories (Optional) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -You'll need to first install some dependencies manually. Unfortunately, ``pylearn2`` isn't yet installable via PyPI and recommends an editable (``pip -e``) installation:: +You'll need to first install some dependencies manually - > pip install numpy scipy theano - > pip install -e git+https://github.com/lisa-lab/pylearn2.git#egg=Package + > pip install numpy scipy theano lasagne Once that's done, you can grab this repository and install from ``setup.py`` in the exact same way:: @@ -132,11 +131,10 @@ The `generated documentation `_ as Links & References ------------------ -* `PyLearn2 `_ by LISA Lab — The amazing neural network library that powers ``sknn``. +* `Lasagne `_ by benanne — The amazing neural network library that powers ``sknn``. * `Theano `_ by LISA Lab — Underlying array/math library for efficient computation. * `scikit-learn `_ by INRIA — Machine learning library with an elegant Pythonic interface. * `nolearn `_ by dnouri — Similar wrapper library for Lasagne compatible with ``scikit-learn``. -* `Lasagne `_ by benanne — Alternative deep learning implementation using ``Theano`` too. ---- diff --git a/docs/pypi.rst b/docs/pypi.rst index da30324..11feb8c 100644 --- a/docs/pypi.rst +++ b/docs/pypi.rst @@ -3,9 +3,9 @@ scikit-neuralnetwork ==================== -Deep neural network implementation without the learning cliff! This library implements multi-layer perceptrons as a wrapper for the powerful ``pylearn2`` library that's compatible with ``scikit-learn`` for a more user-friendly and Pythonic interface. +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 `nucl.ai Conference `_ on **July 20-22**. Join us in **Vienna**! +**NOTE**: This project is possible thanks to the `nucl.ai Conference `_ on **July 18-20**. Join us in **Vienna**! |Documentation Status| |Code Coverage| |License Type| |Project Stars| @@ -14,10 +14,10 @@ Deep neural network implementation without the learning cliff! This library imp Features -------- -Thanks to the underlying ``pylearn2`` implementation, this library supports the following neural network features, which are exposed in an intuitive and `well documented `_ API: +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 —** - * Nonlinear: ``Sigmoid``, ``Tanh``, ``Rectifier``, ``Maxout``. + * Nonlinear: ``Sigmoid``, ``Tanh``, ``Rectifier``. * Linear: ``Linear``, ``Gaussian``, ``Softmax``. * **Layer Types —** ``Convolution`` (greyscale and color, 2D), ``Dense`` (standard, 1D). * **Learning Rules —** ``sgd``, ``momentum``, ``nesterov``, ``adadelta``, ``adagrad``, ``rmsprop``. @@ -34,7 +34,7 @@ To download and setup the latest official release, you can do so from PYPI direc > pip install scikit-neuralnetwork -This contains its own packaged version of ``pylearn2`` from the date of the release (and tag) but will use any globally installed version if available. +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. diff --git a/setup.py b/setup.py index 4166f0f..bb21f5f 100644 --- a/setup.py +++ b/setup.py @@ -21,9 +21,8 @@ install_requires = [ 'scikit-learn', 'theano', - 'pyyaml', 'colorama' if sys.platform == 'win32' else '', - # 'pylearn2', + 'lasagne', ] tests_require = [ @@ -36,7 +35,7 @@ setup(name='scikit-neuralnetwork', version=VERSION, - description="Neural Network wrapper for pylearn2 compatible with scikit-learn.", + description="Deep neural networks without the learning cliff! A wrapper library compatible with scikit-learn.", long_description=README, classifiers=[ "Development Status :: 3 - Alpha",