Use Case and High-Level Description

Face detector based on MobileNetV2 as a backbone with a FCOS head for indoor and outdoor scenes shot by a front-facing camera.



Metric Value
AP (WIDER) 93.57%
GFlops 2.853
MParams 2.392
Source framework PyTorch*

Average Precision (AP) is defined as an area under the precision/recall curve. All numbers were evaluated by taking into account only faces bigger than 64 x 64 pixels.


Image, name: input, shape: 1, 3, 416, 416 in the format B, C, H, W, where:

  • B - batch size
  • C - number of channels
  • H - image height
  • W - image width

Expected color order: BGR.


  1. The boxes is a blob with the shape 200, 5 in the format N, 5, where N is the number of detected bounding boxes. For each detection, the description has the format [x_min, y_min, x_max, y_max, conf], where:
    • (x_min, y_min) - coordinates of the top left bounding box corner
    • (x_max, y_max) - coordinates of the bottom right bounding box corner
    • conf - confidence for the predicted class
  2. The labels is a blob with the shape 200 in the format N, where N is the number of detected bounding boxes. It contains predicted class ID (0 - face) per each detected box.

Training Pipeline

The OpenVINO Training Extensions provide a training pipeline, allowing to fine-tune the model on custom dataset.

Legal Information

[*] Other names and brands may be claimed as the property of others.