The minimum and the recommended requirements to run the Post-training Optimization Tool are the same as in OpenVINO™.
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.
<INSTALL_DIR>/deployment_tools/model_optimizer/install_prerequisites
.<INSTALL_DIR>/deployment_tools/model_optimizer/mo.py -h
.<INSTALL_DIR>/deployment_tools/open_model_zoo/tools/accuracy_checker
.setup.py
script: accuracy_check
alias. To verify it, run accuracy_check -h
.<INSTALL_DIR>/deployment_tools/tools/post_training_optimization_toolkit
.Run the setup.py
script:
In order to enable advanced algorithms such as the Tree-Structured Parzen Estimator (TPE) based optimization, add the following flag to the installation command:
pot
alias. To verify it, run pot -h
.