# mobilefacedet-v1-mxnet¶

## Use Case and High-Level Description¶

MobileFace Detection V1 is a Light and Fast Face Detector for Edge Devices (LFFD) model based on Yolo V3 architecture and trained with MXNet*. For details see the repository and paper.

Metric

Value

Type

Detection

GFLOPs

3.5456

MParams

7.6828

Source framework

MXNet*

Metric

Value

mAP

78.7488%

## Input¶

### Original model¶

Image, name - data, shape - 1, 256, 256, 3, format - B, H, W, C, where:

• B - batch size

• H - height

• W - width

• C - channel

Expected color order - BGR.

### Converted model¶

The converted model has the same parameters as the original model.

WARNING: Please note that the input layout of the converted model is B, H, W, C.

## Output¶

### Original model¶

1. The array of detection summary info, name - yolov30_slice_axis1, shape - 1, 18, 8, 8. The anchor values are 118,157, 186,248, 285,379.

2. The array of detection summary info, name - yolov30_slice_axis2, shape - 1, 18, 16, 16. The anchor values are 43,54, 60,75, 80,106.

3. The array of detection summary info, name - yolov30_slice_axis3, shape - 1, 18, 32, 32. The anchor values are 10,12, 16,20, 23,29.

For each case format is B, N\*DB, Cx, Cy, where:

• B - batch size

• N - number of detection boxes for cell

• DB - size of each detection box

• Cx, Cy - cell index

Detection box has format [x, y, h, w, box_score, face_score], where:

• (x, y) - raw coordinates of box center, apply sigmoid function to get coordinates relative to the cell

• h, w - raw height and width of box, apply exponential function and multiply by corresponding anchors to get height and width values relative to cell

• box_score - confidence of detection box, apply sigmoid function to get confidence in [0, 1] range

• face_score - probability that detected object belongs to face class, apply sigmoid function to get confidence in [0, 1] range

### Converted model¶

1. The array of detection summary info, name - yolov30_yolooutputv30_conv0_fwd/YoloRegion, shape - 1, 18, 8, 8. The anchor values are 118,157, 186,248, 285,379.

2. The array of detection summary info, name - yolov30_yolooutputv31_conv0_fwd/YoloRegion, shape - 1, 18, 16, 16. The anchor values are 43,54, 60,75, 80,106.

3. The array of detection summary info, name - yolov30_yolooutputv32_conv0_fwd/YoloRegion, shape - 1, 18, 32, 32. The anchor values are 10,12, 16,20, 23,29.

For each case format is B, N\*DB, Cx, Cy, where:

• B - batch size

• N - number of detection boxes for cell

• DB - size of each detection box

• Cx, Cy - cell index

Detection box has format [x, y, h, w, box_score, face_score], where:

• (x, y) - raw coordinates of box center to the cell

• h, w - raw height and width of box, apply exponential function and multiply by corresponding anchors to get height and width values relative to cell

• box_score - confidence of detection box in [0, 1] range

• face_score - probability that detected object belongs to face class in [0, 1] range

You can download models and if necessary convert them into OpenVINO™ IR format using the Model Downloader and other automation tools as shown in the examples below.

omz_downloader --name <model_name>

An example of using the Model Converter:

omz_converter --name <model_name>

## Demo usage¶

The model can be used in the following demos provided by the Open Model Zoo to show its capabilities: