The minimum and the recommended requirements to run the Post-training Optimization Tool are the same as in OpenVINO™.
There are two way how to install POT on your system:
This is the simplest way to get POT and OpenVINO™ installed on your PC. Follow the step below to do that:
pip install openvino.
pip install openvino-dev.
Now the POT is available in the command line by the pot alias. To verify it, run
In the instructions below,
<INSTALL_DIR> is the directory where the Intel® distribution of OpenVINO™ toolkit is installed. Post-training Optimization Tool (POT) is distributed as a part of the OpenVINO™ release package, and to use POT as a command-line tool, you need to install OpenVINO™ as well as POT dependencies, namely Model Optimizer and Accuracy Checker. POT source files are available from the
<INSTALL_DIR>/deployment_tools/tools/post_training_optimization_toolkit directory after the OpenVINO™ installation. It is recommended to create a separate Python* environment before installing the OpenVINO™ and its components. To set up the POT in your environment, follow the steps below.
accuracy_checkalias. To verify it, run
In order to enable advanced algorithms such as the Tree-Structured Parzen Estimator (TPE) based optimization, add the following flag to the installation command:
potalias. To verify it, run