1 # OpenVINO™ Calibration Python* package
2 The Inference Engine `openvino.tools.calibration` Python\* package includes types to calibrate a given FP32 model so that you can run it in low-precision 8-bit integer mode while keeping the input data of this model in the original precision.
3 The package has the following dependencies:
4 * `openvino.tools.accuracy_checker` package
5 * `openvino.tools.benchmark` package.
7 Please, refer to https://docs.openvinotoolkit.org for details.
10 You can use the `openvino.tools.calibration` package in a simple way:
12 import openvino.tools.calibration as calibration
14 with calibration.CommandLineProcessor.process() as config:
15 network = calibration.Calibrator(config).run()
17 network.serialize(config.output_model)
20 1. Import openvino.tools.calibration types:
22 import openvino.tools.calibration as calibration
25 2. Read configuration and process the model:
27 config = calibration.CommandLineProcessor.process()
30 3. Serialize result model:
32 network.serialize(config.output_model)