# DEKR
DEKR estimates multi-person poses from image-wide keypoint heatmaps and offsets.
Tasks: Pose. Install: pip install libreyolo.
Verified against LibreYOLO v1.6.0.

## Install

```bash
pip install "libreyolo"
```

## Predict

**Python**

```python
from libreyolo import LibreYOLO, SAMPLE_IMAGE

# Downloads the W32 checkpoint from the upstream CDN and checks its SHA-256
model = LibreYOLO("LibreDEKRw32-pose.pt", device="cpu")
result = model(SAMPLE_IMAGE)
print(result.keypoints)
```

The adapter uses the W32 no-deformable-convolution graph and 17 COCO person keypoints. Boxes enclose confident decoded joints. This is an inference-only family; the original deformable graph is a different checkpoint architecture.


## Validate

**Python**

```python
from libreyolo import LibreYOLO

# Downloads the W32 checkpoint from the upstream CDN and checks its SHA-256
model = LibreYOLO("LibreDEKRw32-pose.pt", device="cpu")
# coco8-pose.yaml builds a 4-image COCO keypoint split on first use
metrics = model.val(data="coco8-pose.yaml", allow_download_scripts=True, workers=0)
print(metrics)
```

Use the dataset format for this task. [Validation](/docs/train/validation) explains the dataset requirements and returned metrics.

## Export

| Task | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | ncnn | TFLite | CoreML | Core AI |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Pose | yes | yes |  | yes | yes |  |  |  |  |  |  |  |

A "yes" means the export is supported. An empty cell means the exporter refuses that combination.

**Python**

```python
from libreyolo import LibreYOLO

# Downloads the W32 checkpoint from the upstream CDN and checks its SHA-256
model = LibreYOLO("LibreDEKRw32-pose.pt", device="cpu")
model.export(format="onnx")
```

[Export setup](/docs/export) lists format dependencies and loading exported artifacts.

## Licensing

Check the license on the Hugging Face repository of the specific weights you download. That repository is authoritative and licenses are not always uniform across a family. This is a description of the licenses involved, not legal advice.

- Original work: DEKR, HRNet authors
- Upstream license: MIT
- Upstream source: https://github.com/HRNet/DEKR
- LibreYOLO code: MIT
- Weights: MIT, distributed by their authors. LibreYOLO does not host or mirror them.
- Interpretation: The upstream implementation is MIT. The adapter retrieves the released checkpoint from its source CDN.

## Citation

```bibtex
@inproceedings{GengSXZW21,
  title={Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression},
  author={Zigang Geng, Ke Sun, Bin Xiao, Zhaoxiang Zhang, Jingdong Wang},
  booktitle={CVPR},
  year={2021}
}
```

Copied from https://raw.githubusercontent.com/HRNet/DEKR/main/README.md