We suggest to install or use the package in the Python virtual environment.
If you want to optimize a model from PyTorch, install PyTorch by following PyTorch installation guide. For other backend follow: TensorFlow installation guide, ONNX installation guide, OpenVINO installation guide.
NNCF can be installed as a regular PyPI package via pip:
pip install nncfIf you want to install both NNCF and the supported PyTorch version in one line, you can do this by simply running:
pip install nncf[torch]Other viable options besides [torch] are [tf], [onnx] and [openvino].
Install the package and its dependencies by running the following command in the repository root directory:
pip install .Use the same pip install syntax as above to install NNCF along with the backend package version in one go:
pip install .[<BACKEND>]List of supported backends: torch, tf, onnx and openvino.
For development purposes install extra packages by
pip install .[dev,tests]NB: For launching example scripts in this repository, we recommend setting the PYTHONPATH variable to the root of the checked-out repository once the installation is completed.
NNCF is also available via conda:
conda install -c conda-forge nncfpip install git+https://github.com/openvinotoolkit/nncf@bd189e2#egg=nncfNote that in order for this to work for pip versions >= 21.3, your Git version must be at least 2.22.
The following table lists the recommended corresponding versions of backend packages as well as the supported versions of Python:
| NNCF | OpenVINO | PyTorch | ONNX | TensorFlow | Python |
|---|---|---|---|---|---|
develop |
2023.3.0 |
2.1.2 |
1.13.1 |
2.12.0 |
3.8 |
2.8.0 |
2023.3.0 |
2.1.2 |
1.13.1 |
2.12.0 |
3.8 |
2.7.0 |
2023.2.0 |
2.1 |
1.13.1 |
2.12.0 |
3.8 |
2.6.0 |
2023.1.0 |
2.0.1 |
1.13.1 |
2.12.0 |
3.8 |
2.5.0 |
2023.0.0 |
1.13.1 |
1.13.1 |
2.11.1 |
3.8 |
2.4.0 |
2022.1.0 |
1.12.1 |
1.12.0 |
2.8.2 |
3.8 |