ultra-lightweight-face-detection-slim-320¶

Use Case and High-Level Description¶

Ultra-lightweight Face Detection slim 320 is a version of the lightweight face detection model with network backbone simplification. The model designed for edge computing devices and pre-trained on the WIDER FACE dataset with 320x240 input resolutions.

For details see repository.

Metric

Value

Type

Object detection

GFLOPs

0.1724

MParams

0.2844

Source framework

PyTorch*

Metric

Value

mAP

83.32%

Input¶

Original model¶

Image, name - input, shape - 1, 3, 240, 320, format B, C, H, W, where:

• B - batch size

• C - number of channels

• H - image height

• W - image width

Expected color order is RGB.

Mean values - [127.0, 127.0, 127.0]. Scale values - [128.0, 128.0, 128.0].

Converted model¶

Image, name - input, shape - 1, 3, 240, 320, format B, C, H, W, where:

• B - batch size

• C - number of channels

• H - image height

• W - image width

Expected color order is BGR.

Output¶

Original model¶

1. Bounding boxes, name: boxes, shape - 1, 4420, 4. Presented in format B, A, 4, where:

• B - batch size

• A - number of detected anchors

For each detection, the description has the format: [x_min, y_min, x_max, y_max], where:

• (x_min, y_min) - coordinates of the top left bounding box corner (coordinates are in normalized format, in range [0, 1])

• (x_max, y_max) - coordinates of the bottom right bounding box corner (coordinates are in normalized format, in range [0, 1])

2. Scores, name: scores, shape - 1, 4420, 2. Contains scores for 2 classes - the first is background, the second is face.

Converted model¶

1. Bounding boxes, name: boxes, shape - 1, 4420, 4. Presented in format B, A, 4, where:

• B - batch size

• A - number of detected anchors

For each detection, the description has the format: [x_min, y_min, x_max, y_max], where:

• (x_min, y_min) - coordinates of the top left bounding box corner (coordinates are in normalized format, in range [0, 1])

• (x_max, y_max) - coordinates of the bottom right bounding box corner (coordinates are in normalized format, in range [0, 1])

2. Scores, name: scores, shape - 1, 4420, 2. Contains scores for 2 classes - the first is background, the second is face.

python3 <omz_dir>/tools/downloader/downloader.py --name <model_name>
python3 <omz_dir>/tools/downloader/converter.py --name <model_name>