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.
The original model is distributed under the following license: