Use Case and High-Level Description
Face detector for driver monitoring and similar scenarios. The network features a default MobileNet backbone that includes depth-wise convolutions to reduce the amount of computation for the 3x3 convolution block.
Example
Specification
| Metric | Value |
|---|---|
| AP (head height >10px) | 37.4% |
| AP (head height >32px) | 84.8% |
| AP (head height >64px) | 93.1% |
| AP (head height >100px) | 94.1% |
| Min head size | 90x90 pixels on 1080p |
| GFlops | 2.835 |
| MParams | 1.053 |
| Source framework | Caffe* |
Average Precision (AP) is defined as an area under the precision/recall curve. Numbers are on Wider Face validation subset.
Performance
Inputs
Name: input, shape: [1x3x384x672] - 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.
Outputs
The net outputs blob with shape: [1, 1, N, 7], where N is the number of detected bounding boxes. The results are sorted by confidence in decreasing order. 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 batchlabel- predicted class IDconf- 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.
Legal Information
[*] Other names and brands may be claimed as the property of others.