You can find announced in 2019 R1 OpenVINO™ Calibration Tool sample configuration files in attached ZIP.
ZIP file includes
- definitions.yml - definition file
- inception_v1.yml - configuration file for Tensorflow* Inception v1 model
- ssd_mobilenet_v1_coco.yml - configuration file for Tensorflow* SSD Mobilenet v1 model
- unet2d.yml - configuration file for Unet2D mode in in OpenVINO* Inference Engine Intermediate Representation format
Let me know if you have any questions.
Best regards, Edward
And for custom models that don't have config files yet, here is the workflow for handling this:
- Convert annotation of your dataset. Use one of the converters from annotation-converters, or write your own if there is no converter for your dataset. You can find detailed instruction how to use converters in Annotation Conversion Guide.
- Choose one of adapters or write your own. Adapter converts raw output produced by framework to high level problem specific representation (e.g. ClassificationPrediction, DetectionPrediction, etc).
- Reproduce preprocessing, metrics and postprocessing from canonical paper.
- Create entry in config file and execute.