Use Case and High-Level Description

This is a person, vehicle, bike detector that is based on MobileNetV2 backbone with two SSD heads from 1/16 and 1/8 scale feature maps and clustered prior boxes for 512x512 resolution.



Metric Value
AP @ [ IoU=0.50:0.95 ] 0.248 (internal test set)
GFlops 3.146
MParams 1.821
Source framework PyTorch*


Image, name: input, shape: 1, 3, 512, 512 in the format B, C, H, W, where:

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

Expected color order is BGR.


The net outputs blob with shape: 1, 1, 200, 7 in the format 1, 1, N, 7, where N is the number of detected bounding boxes. Each detection has the format [image_id, label, conf, x_min, y_min, x_max, y_max], where:

  • image_id - ID of the image in the batch
  • label - predicted class ID (0 - vehicle, 1 - person, 2 - bike)
  • conf - confidence for the predicted class
  • (x_min, y_min) - coordinates of the top left bounding box corner
  • (x_max, y_max) - coordinates of the bottom right bounding box corner

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.