Installation

Attention

As of July 7, 2025, the latest opencv-python package introduces conflicting dependencies.

Before installing any version of MetaTF, you must run:

pip install opencv-python==4.11.0.86

From MetaTF 2.15 onward, this issue will no longer occur.

Supported configurations

• Operating systems:

  • Windows 10, Windows 11

  • Any Linux variant compatible with manylinux 2.28 (Ubuntu 20.04, Ubuntu 22.04, …)

• Python versions: 3.9 to 3.11

• TensorFlow versions: 2.15

Warning

Using Windows, the latest Visual C++ redistributable package is required. Please refer to this link for installation.

Quick installation

Warning

TensorFlow package is required to use the CNN2SNN tool, the Akida model zoo and to run the examples. Please refer to Install TensorFlow with pip for installation.

The akida, CNN2SNN and akida_models python packages can be setup with Python’s pip package manager:

pip install akida==2.14.0
pip install cnn2snn==2.14.0
pip install akida-models==1.8.0

Note

We recommend using virtual environment such as Conda. Please note that the python version must be explicitly specified when creating a conda environment. The specification must be for one of the supported python versions listed above.

conda create --name akida_env python=3.11
conda activate akida_env

Running examples

The Akida tutorials can be downloaded from the examples section as python scripts or Jupyter Notebooks. Dependencies needed to replay the examples can be installed using the requirements.txt file:

pip install -r requirements.txt

Note

Please refer to this link for Jupyter Notebook installation and configuration.