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) | 54.3% |
| GFlops | 14.3253 |
| MParams | 8.1506 |
| Source framework | PyTorch* |
Average Precision metric described in COCO Keypoint Evaluation site.
Name: input, shape: 1, 3, 448, 448. An input image 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 BGR.
The net outputs three blobs:
heatmapsof shapeB, 17, 224, 224containing location heatmaps for keypoints of all types. Locations that are filtered out by non-maximum suppression algorithm have negated values assigned to them.embeddingsof shapeB, 17, 224, 224, 1containing associative embedding values, which are used for grouping individual keypoints into poses.
[*] Other names and brands may be claimed as the property of others.