Face detector based on MobileNetV2 as a backbone with a multiple SSD head for indoor/outdoor scenes shot by a front-facing camera. During training of this model training images were resized to 384x384.
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.
Name: "input" , shape: [1x3x384x384] - An input image in the format [BxCxHxW], where:
Expected color order - BGR.
The net outputs a blob with shape: [1, 1, N, 7], where N is the number of detected bounding boxes. For each detection, the description has the format: [
image_id- ID of the image in the batch
label- predicted class ID
conf- confidence for the predicted class
y_min) - coordinates of the top left bounding box corner
y_max) - coordinates of the bottom right bounding box corner.
[*] Other names and brands may be claimed as the property of others.