metadata
license: apache-2.0
datasets:
- detection-datasets/coco
language:
- en
metrics:
- accuracy
tags:
- RyzenAI
- pose estimation
MoveNet
MoveNet is an ultra fast and accurate model that detects 17 keypoints of a body. It released in movenet.pytorch
We develop a modified version that could be supported by AMD Ryzen AI.
How to use
Installation
Follow Ryzen AI Installation to prepare the environment for Ryzen AI. Run the following script to install pre-requisites for this model.
pip install -r requirements.txt
Data Preparation (optional: for accuracy evaluation)
1.Download COCO dataset2017 from https://cocodataset.org/. (You need train2017.zip, val2017.zip and annotations.)Unzip to ./data/ like this:
├── data
├── annotations (person_keypoints_train2017.json, person_keypoints_val2017.json, ...)
├── train2017 (xx.jpg, xx.jpg,...)
└── val2017 (xx.jpg, xx.jpg,...)
2.Make data to our data format.
- Modify the path in line 282~287 in make_coco_data_17keypoints.py if needed
- run the code to pre-process the dataset
python make_coco_data_17keypoints.py
Our data format: JSON file
Keypoints order:['nose', 'left_eye', 'right_eye', 'left_ear', 'right_ear',
'left_shoulder', 'right_shoulder', 'left_elbow', 'right_elbow', 'left_wrist',
'right_wrist', 'left_hip', 'right_hip', 'left_knee', 'right_knee', 'left_ankle',
'right_ankle']
One item:
[{"img_name": "0.jpg",
"keypoints": [x0,y0,z0,x1,y1,z1,...],
#z: 0 for no label, 1 for labeled but invisible, 2 for labeled and visible
"center": [x,y],
"bbox":[x0,y0,x1,y1],
"other_centers": [[x0,y0],[x1,y1],...],
"other_keypoints": [[[x0,y0],[x1,y1],...],[[x0,y0],[x1,y1],...],...], #lenth = num_keypoints
},
...
]
Test & Evaluation
- Modify the DATASET_PATH in eval_onnx.py if needed
- Test accuracy of the quantized model
python eval_onnx.py --ipu --provider_config Path\To\vaip_config.json
Performance
| Metric | Accuracy on IPU |
|---|---|
| accuracy | 79.745% |