Use Post-Training Optimization Tool Command-Line Interface¶
POT command-line interface (CLI) is designed to optimize models that are supported by the Accuracy Checker Tool used for accuracy measurement. If your model is exactly from the OpenVINO Model Zoo or it is similar to one of its models then you can employ POT CLI to optimize your model. In other cases, you should consider using POT API. To start with POT CLI please refer to the following example.
Note
There is also the so-called **Simplified mode** that is basically aimed at INT8 quantization if the model is from the Computer Vision domain and has a simple dataset preprocessing, like image resize and crop. In this case, you can also use POT CLI for
optimization. However, the accuracy results are not guaranteed in this case. Moreover, you are also limited in the optimization methods choice since the accuracy measurement is not available.
Prerequisites¶
Install POT following the Installation Guide.
Convert your model from the framework representation into the OpenVINO IR format with the Model Optimizer.
Prepare the Accuracy Checker configuration file and make sure that the model can be successfully inferred and achieves similar accuracy numbers as the reference model from the original framework.
Activate the Python environment in the command-line shell where the POT and the Accuracy Checker were installed.
(Optional). Set up the OpenVINO environment in the command-line shell with the following script if you installed it from form the distribution file:
source <INSTALL_DIR>/bin/setupvars.sh
Note
This step is not required if you use PyPI distribution.
There are two ways how to run POT via command line:
Basic usage. In this case you can run POT with basic setting just specifying all the options via command line:
pot -q default -m <path_to_xml> -w <path_to_bin> --ac-config <path_to_AC_config_yml>
Advanced usage. In this case you should prepare a configuration file for the POT where you can specify advanced options for the optimization methods available. See POT configuration file description for more details. To launch the command-line tool with the configuration file run:
pot -c <path_to_config_file>
For all available usage options, use the
-h
,--help
arguments or refer to the Command-Line Arguments section below.
By default, the results are dumped into the separate output subfolder inside the ./results
folder that is created in the same directory where the tool is run from. Use the -e
option to evaluate the accuracy directly from the tool.
See also the How to Run Examples tutorial about how to run a particular example of 8-bit quantization with the POT.
Command-Line Arguments¶
The following command-line options are available to run the tool:
Argument |
Description |
---|---|
|
Optional. Show help message and exit. |
|
Quantize model to 8 bits with specified quantization method: |
|
Use |
|
Path to the optimizing model file (.xml). Applicable only when |
|
Path to the weights file of the optimizing model (.bin). Applicable only when |
|
Model name. Applicable only when |
|
Path to the Accuracy Checker configuration file. Applicable only when |
|
Optional. Maximum accuracy drop. Valid only for accuracy-aware quantization. Applicable only when |
|
Path to a config file with task- or model-specific parameters. |
|
Optional. Evaluate model on the whole dataset after optimization. |
|
Optional. A directory where results are saved. Default: |
|
Optional. Save the original full-precision model. |
|
Optional. Save results directly to output directory without additional subfolders. |
|
Optional. Log level to print. Default: INFO. |
|
Optional. Disable CL logging and enable progress bar. |
|
Optional. Switch model quantization progress display to a multiline mode. Use with third-party components. |
|
Optional. Keep Convolution, Deconvolution and FullyConnected weights uncompressed. Use with third-party components. |