This is a multi-person 2D pose estimation network (based on the OpenPose approach) with tuned MobileNet v1 as a feature extractor. For every person in an image, the network detects a human pose: a body skeleton consisting of keypoints and connections between them. The pose may contain up to 18 keypoints: ears, eyes, nose, neck, shoulders, elbows, wrists, hips, knees, and ankles.
|Average Precision (AP)||42.8%|
Average Precision metric described in COCO Keypoint Evaluation site.
Tested on a COCO validation subset from the original paper Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields.
1, 3, 256, 456 in the
B, C, H, W format, where:
B- batch size
C- number of channels
H- image height
W- image width
Expected color order is
The net outputs are two blobs:
1, 38, 32, 57contains keypoint pairwise relations (part affinity fields).
1, 19, 32, 57contains keypoint heatmaps.
[*] Other names and brands may be claimed as the property of others.