This is a multi-person 2D pose estimation network based on the EfficientHRNet approach (that follows the Associative Embedding framework). 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 17 keypoints: ears, eyes, nose, shoulders, elbows, wrists, hips, knees, and ankles.
Metric | Value |
---|---|
Average Precision (AP) | 50.2% |
GFlops | 8.8720 |
MParams | 8.1504 |
Source framework | PyTorch* |
Average Precision metric described in COCO Keypoint Evaluation site.
Name: input
, shape: [1x3x352x352]. An input image in the [BxCxHxW] format , where:
The net outputs three blobs:
[*] Other names and brands may be claimed as the property of others.