Installation¶
Installing Keras Spiking¶
We recommend using pip
to install Keras Spiking:
pip install keras-spiking
That’s it!
Requirements¶
Keras Spiking works with Python 3.6 or later. pip
will do its best to install
all of Keras Spiking’s requirements automatically. However, if anything
goes wrong during this process you can install the requirements manually and
then try to pip install keras-spiking
again.
Developer installation¶
If you want to modify Keras Spiking, or get the very latest updates, you will need to perform a developer installation:
git clone https://github.com/nengo/keras-spiking.git
pip install -e ./keras-spiking
Installing TensorFlow¶
Use pip install tensorflow
to install the latest version of TensorFlow. GPU support
is included in this package as of version 2.1.0.
In order to use TensorFlow with GPU support you will need to install the appropriate
Nvidia drivers and CUDA/cuDNN. The precise steps for accomplishing this will depend
on your system. On Linux the correct Nvidia drivers (as of TensorFlow 2.2.0) can be
installed via sudo apt install nvidia-driver-440
, and on Windows simply using the
most up-to-date drivers should work. For CUDA/cuDNN we recommend using
conda to
simplify the process. conda install tensorflow-gpu
will install TensorFlow as
well as all the CUDA/cuDNN requirements. If you run into any problems, see the
TensorFlow GPU installation instructions
for more details.
It is also possible to build TensorFlow from source. This is significantly more complicated but allows you to customize the installation to your computer, which can improve simulation speeds.