Use Case and High-Level Description

This is a person detector that is based on MobileNetV2 backbone with ATSS head for 864x480 resolution.



Metric Value
AP @ [ IoU=0.50:0.95 ] 0.408 (internal test set)
GFlops 6.519
MParams 2.394
Source framework PyTorch*

Average Precision (AP) is defined as an area under the precision/recall curve.


Name: input, shape: [1x3x480x864] - An input image in the format [BxCxHxW], where:

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

Expected color order is BGR.


  1. The boxes is a blob with shape: [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 shape: [N], where N is the number of detected bounding boxes. In case of person detection, it is equal to 1 for each detected box with person in it and 0 for the background.

Legal Information

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