RetinaFace-Anti-Cov is a customized one stage face detector to help people protect themselves from CovID-19. More details provided in the paper and repository
Metric | Value |
---|---|
Type | Object detection, object attributes, facial landmarks |
GFLOPs | 2.7781 |
MParams | 0.5955 |
Source framework | MXNet* |
Metric | Value |
---|---|
mAP | 77.1531% |
Image, name - data
, shape - [1x3x640x640], format [BxCxHxW], where:
Expected color order - RGB.
Image, name - data
, shape - [1x3x640x640], format [BxCxHxW], where:
Expected color order - BGR.
Model outputs are floating points tensors:
face_rpn_cls_prob_reshape_stride32
, shape: 1,4, 20, 20
, format: [B, Ax2, H, W]
, represents detection scores from Feature Pyramid Network (FPN) level with stride 32 for 2 classes: background and face.face_rpn_bbox_stride32
, shape: 1,8,20,20
, format: [B, Ax4, H, W]
, represents detection box deltas from Feature Pyramid Network (FPN) level with stride 32.face_rpn_landmark_pred_stride32
, shape: 1,20,20,20
, format: [B, Ax10, H, W]
, represents facial landmarks from Feature Pyramid Network (FPN) level with stride 32.face_rpn_type_prob_reshape_stride32
, shape: 1,6,20,20
, format: [B, Ax3, H, W]
, represents attributes score.face_rpn_cls_prob_reshape_stride16
, shape: 1,4,40,40
, format: [B, Ax2, H, W]
, represents detection scores from Feature Pyramid Network (FPN) level with stride 16 for 2 classes: background and face.face_rpn_bbox_stride16
, shape: 1,8,40,40
, format: [B, Ax4, H, W]
, represents detection box deltas from Feature Pyramid Network (FPN) level with stride 16.face_rpn_landmark_pred_stride16
, shape: 1,20,40,40
, format: [B, Ax10, H, W]
, represents facial landmarks from Feature Pyramid Network (FPN) level with stride 16.face_rpn_type_prob_reshape_stride16
, shape: 1,6,40,40
, format: [B, Ax3, H, W]
, represents attributes score.face_rpn_cls_prob_reshape_stride16
, shape: 1,4,80,80
, format: [B, Ax2, H, W]
, represents detection scores from Feature Pyramid Network (FPN) level with stride 8 for 2 classes: background and face.face_rpn_bbox_stride16
, shape: 1,8,80,80
, format: [B, Ax4, H, W]
, represents detection box deltas from Feature Pyramid Network (FPN) level with stride 8.face_rpn_landmark_pred_stride16
, shape: 1,20,80,80
, format: [B, Ax10, H, W]
, represents facial landmarks from Feature Pyramid Network (FPN) level with stride 8.face_rpn_type_prob_reshape_stride8
, shape: 1,6,80,80
, format: [B, Ax3, H, W]
, represents attributes score.For each output format:
B
- batch sizeA
- number of anchorsH
- feature heightW
- feature widthDetection box deltas have format [dx, dy, dh, dw]
, where:
(dx, dy)
- regression for left-upper corner of bounding box,(dh, dw)
- regression by height and width of bounding box.Facial landmarks have format [x1, y1, x2, y2, x3, y3, x4, y4, x5, y5]
, where:
(x1, y1)
- coordinates of left eye(x2, y2)
- coordinates of rights eye(x3, y3)
- coordinates of nose(x4, y4)
- coordinates of left mouth corner(x5, y5)
- coordinates of right mouth cornerThe third element in attributes score is a mask attribute. This score determines the presence or absence of a mask on a person.
The converted model has the same parameters as the original model.
You can download models and if necessary convert them into Inference Engine format using the Model Downloader and other automation tools as shown in the examples below.
An example of using the Model Downloader:
An example of using the Model Converter:
The original model is distributed under the following license: