This is a person detector for the ASL Recognition scenario. It is based on ShuffleNetV2-like backbone that includes depth-wise convolutions to reduce the amount of computation for the 3x3 convolution block and FCOS head.
|Persons AP on MS-COCO*||77.68%|
|Minimal person height||100 pixel|
Average Precision (AP) is defined as an area under the precision/recall curve.
Name: "input" , shape: [1x3x320x320] - An input image in the format [1xCxHxW], where:
Expected color order is BGR.
The net outputs blob with shape: [N, 5], where N is the number of detected bounding boxes. For each detection, the description has the format: [
y_min) - coordinates of the top left bounding box corner
y_max) - coordinates of the bottom right bounding box corner.
conf- confidence for the predicted class
[*] Other names and brands may be claimed as the property of others.