Installation

Requirements

  • python 2.7 or python >= 3.4
  • numpy >= 1.11.0
  • nengo >= 2.3.1
  • tensorflow >= 1.0.0

Installing NengoDL

To install NengoDL, we recommend using pip:

pip install nengo_dl

pip will do its best to install all of NengoDL’s requirements when it installs NengoDL. However, if anything goes wrong during this process you can install the requirements manually. See the Nengo documentation for instructions on installing numpy and nengo, and the tensorflow installation instructions below.

Developer installation

If you want to modify NengoDL, or get the very latest updates, you will need to perform a developer installation:

git clone https://github.com/nengo/nengo_dl.git
cd nengo_dl
python setup.py develop --user

If you are in a virtual environment (recommended), you can omit the --user flag.

Installing TensorFlow

Use pip install tensorflow to install the minimal version of TensorFlow, or pip install tensorflow-gpu to include GPU support.

It is also possible to install TensorFlow from source. This is significantly more complicated but allows you to customize the installation to your computer, which can improve simulation speeds.

Instructions for installing on Ubuntu or Mac OS.

Instructions for installing on Windows.