[Deprecated] Quantizing Cascaded Face detection Model

Danger

Post-training Optimization Tool is deprecated since OpenVINO 2023.0. Neural Network Compression Framework (NNCF) is recommended for the post-training quantization instead.

This example demonstrates the use of the Post-training Optimization Tool API for the task of quantizing a face detection model. The MTCNN model from Caffe is used for this purpose. A custom DataLoader is created to load the WIDER FACE dataset for a face detection task and the implementation of Recall metric is used for the model evaluation. In addition, this example demonstrates how one can implement an engine to infer a cascaded (composite) model that is represented by multiple submodels in an OpenVINO™ Intermediate Representation (IR) and has a complex staged inference pipeline. The code of the example is available on GitHub.

How to Prepare the Data

To run this example, you need to download the validation part of the Wider Face dataset http://shuoyang1213.me/WIDERFACE/. Images with faces divided into categories are placed in the WIDER_val/images folder. Annotations in .txt format containing the coordinates of the face bounding boxes of the validation part of the dataset can be downloaded separately and are located in the wider_face_split/wider_face_val_bbx_gt.txt file.

How to Run the Example

  1. Launch Model Downloader tool to download mtcnn model from the Open Model Zoo repository.

    omz_downloader --name mtcnn*
    
  2. Launch Model Converter tool to generate Intermediate Representation (IR) files for the model:

    omz_converter --name mtcnn* --mo <PATH_TO_MODEL_OPTIMIZER>/mo.py
    
  3. Launch the example script from the example directory:

    python3 ./face_detection_example.py -pm <PATH_TO_IR_XML_OF_PNET_MODEL>
    -rm <PATH_TO_IR_XML_OF_RNET_MODEL> -om <PATH_TO_IR_XML_OF_ONET_MODEL> -d <WIDER_val/images> -a <wider_face_split/wider_face_val_bbx_gt.txt>
    

    Optional: you can specify .bin files of corresponding IRs directly using the -pw/--pnet-weights, -rw/--rnet-weights and -ow/--onet-weights options.