face-detection-0206

Use Case and High-Level Description

Face detector based on ResNet152 as a backbone with a ATSS head for indoor and outdoor scenes shot by a front-facing camera.

Example

_images/face-detection-0206.png

Specification

Metric

Value

AP ( WIDER )

94.27%

GFlops

339.602

MParams

69.920

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.

Inputs

Image, name: input, shape: 1, 3, 640, 640 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.

Outputs

  1. The boxes is a blob with the shape 750, 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 750 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.

Use Case and High-Level Description

Face detector based on ResNet152 as a backbone with a ATSS head for indoor and outdoor scenes shot by a front-facing camera.

Example

_images/face-detection-0206.png

Specification

Metric

Value

AP ( WIDER )

94.27%

GFlops

339.602

MParams

69.920

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.

Inputs

Image, name: input, shape: 1, 3, 640, 640 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.

Outputs

  1. The boxes is a blob with the shape 750, 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 750 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.