Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.
5541 Discussions

Sample configuration files for Calibration Tool

Edward_S_Intel1
Employee
215 Views

Hi guys,

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

0 Kudos
3 Replies
ChunShen_S_Intel
Employee
215 Views

May I ask since the configuration files available inside openVINO are so limited, how can I get the configuration file for other model for example SSD MobileNetV2?

Roy_A_Intel
Employee
215 Views

Hi Sea, 

There are additional config files (13)  available under C:\Program Files (x86)\IntelSWTools\openvino_2019.2.242\deployment_tools\open_model_zoo\tools\accuracy_checker\configs. 

Roy_A_Intel
Employee
215 Views

And for custom models that don't have config files yet, here is the workflow for handling this:

  1. 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.
  2. 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).
  3. Reproduce preprocessing, metrics and postprocessing from canonical paper.
  4. Create entry in config file and execute.
Reply