You have multiple options to get up and running, though using
pip is by far the easiest and most reliable.
A) Download Latest Release [Recommended]¶
If you want to use the latest official release, you can do so from PYPI directly:
> pip install scikit-neuralnetwork
This will install the latest official
Theano as well as other minor packages too as a dependency. We strongly suggest you use a virtualenv for Python.
B) Pulling Repositories [Optional]¶
If you want to use the more advanced features like convolution, pooling or upscaling, these depend on the latest code from
Theano master branches. You can install them manually as follows:
> pip install -r https://raw.githubusercontent.com/aigamedev/scikit-neuralnetwork/master/requirements.txt
Once that’s done, you can grab this repository and install from
setup.py in the exact same way:
> git clone https://github.com/aigamedev/scikit-neuralnetwork.git > cd scikit-neuralnetwork; python setup.py develop
This will make the
sknn package globally available within Python as a reference to the current directory.
We encourage you to launch the tests to check everything is working using the following commands:
> pip install nose > nosetests -v sknn
Use the additional command-line parameters in the test runner
--process-timeout=60 to speed things up on powerful machines. The result should look as follows in your terminal.
We strive to maintain 100% test coverage for all code-paths, to ensure that rapid changes in the underlying
Theano libraries are caught automatically.