HRNet is an advanced deep learning architecture for human pose estimation, characterized by its maintenance of high-resolution representations throughout the entire network process, thereby avoiding the low-to-high resolution recovery step typical of traditional models. The network features parallel multi-resolution subnetworks and enriches feature representation through repeated multi-scale fusion, which enhances the accuracy of keypoint detection. Additionally, HRNet offers computational efficiency and has demonstrated superior performance over previous methods on several standard datasets.
| GPU | IXUCA SDK | Release | Branch |
|---|---|---|---|
| MR-V100 | 4.4.0 | 26.03 | release/26.03 |
| MR-V100 | 4.3.0 | 25.12 | release/25.12 |
Note: 请切换到与您的 SDK 版本对应的 Release 分支进行测试。请勿直接在 master 分支上运行测试，因为 master 分支可能包含与您的本地 SDK 版本不兼容的最新更改。
切换分支命令示例：
git checkout release/26.03
Pretrained model: https://download.openmmlab.com/mmdetection/v2.0/hrnet/fcos_hrnetv2p_w18_gn-head_4x4_1x_coco/fcos_hrnetv2p_w18_gn-head_4x4_1x_coco_20201212_100710-4ad151de.pth
Dataset:
- https://github.com/ultralytics/assets/releases/download/v0.0.0/coco2017labels.zip to download the labels dataset.
- http://images.cocodataset.org/zips/val2017.zip to download the validation dataset.
- http://images.cocodataset.org/zips/train2017.zip to download the train dataset.
unzip -q -d ./ coco2017labels.zip
unzip -q -d ./coco/images/ train2017.zip
unzip -q -d ./coco/images/ val2017.zip
coco
├── annotations
│ └── instances_val2017.json
├── images
│ ├── train2017
│ └── val2017
├── labels
│ ├── train2017
│ └── val2017
├── LICENSE
├── README.txt
├── test-dev2017.txt
├── train2017.cache
├── train2017.txt
├── val2017.cache
└── val2017.txtContact the Iluvatar administrator to get the missing packages:
- mmcv-*.whl
# Install libGL
## CentOS
yum install -y mesa-libGL
## Ubuntu
apt install -y libgl1-mesa-glx
pip3 install -r requirements.txt# export onnx model
python3 export.py --weight fcos_hrnetv2p_w18_gn-head_4x4_1x_coco_20201212_100710-4ad151de.pth --cfg fcos_hrnetv2p-w18-gn-head_4xb4-1x_coco.py --output hrnet.onnx
# Use onnxsim optimize onnx model
onnxsim hrnet.onnx hrnet_opt.onnxexport DATASETS_DIR=/Path/to/coco/# Accuracy
bash scripts/infer_hrnet_fp16_accuracy.sh
# Performance
bash scripts/infer_hrnet_fp16_performance.sh| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 |
|---|---|---|---|---|---|
| HRNet | 32 | FP16 | 64.282 | 0.491 | 0.326 |