tffpy requires the following packages, which will be automatically installed with tffpy using pip:

Make sure your Python environment is properly configured. It is recommended to install tffpy in a virtual environment.

Release version

First, make sure you have the latest version of pip (the Python package manager) installed. If you do not, refer to the Pip documentation and install pip first.

Install the current release with pip:

pip install tffpy

To upgrade to a newer release use the --upgrade flag:

pip install --upgrade tffpy

If you do not have permission to install software systemwide, you can install into your user directory using the --user flag:

pip install --user tffpy

Alternatively, you can manually download tffpy from its GitLab project or PyPI. To install one of these versions, unpack it and run the following from the top-level source directory using the Terminal:

pip install .

Dataset installation

Download the data from this link.

Then run function tffpy.utils.generate_config() in order to create a configuration file and modify it to specify the path to your data folder. The location of the configuration file is given by function tffpy.utils.get_config_file().

Development version

If you have Git installed on your system, it is also possible to install the development version of tffpy.

Before installing the development version, you may need to uninstall the standard version of tffpy using pip:

pip uninstall tffpy

Clone the Git repository:

git clone
cd python

You may also need to install required packages:

pip install -r requirements/defaults.txt

Then execute pip with flag -e to follow the development branch:

pip install -e .

To update tffpy at any time, in the same directory do:

git pull

To run unitary tests, first install required packages:

pip install -r requirements/dev.txt

and execute pytest: