ONNX 模型库
返回模型

说明文档

YOLO26-Pose

此版本的 YOLOv26-Pose 已转换为使用 w8a16 量化在 Axera NPU 上运行。

兼容 Pulsar2 版本：4.2。

转换工具链接：

如果您对模型转换感兴趣，可以通过以下方式导出 axmodel：

支持平台

性能统计

AX650N(NPU1)

模型 FPS CMM(MB) 延迟(ms)
yolo26n-pose 240.21 5.71 4.163
yolo26s-pose 99.30 17.90 10.070
yolo26m-pose 36.96 37.82 27.053
yolo26l-pose 28.88 39.25 34.620
yolo26x-pose 13.50 79.61 74.072

AX650N(NPU3)

模型 FPS CMM(MB) 延迟(ms)
yolo26n-pose 655.74 3.80 1.525
yolo26s-pose 283.45 11.27 3.528
yolo26m-pose 107.57 28.98 9.296
yolo26l-pose 83.59 35.22 11.963
yolo26x-pose 39.80 72.24 25.128

AX630C

模型 延迟(ms) npu1 延迟(ms) npu2
yolo26n-pose 11.003 7.203
yolo26s-pose 24.157 17.120

AX615

模型 延迟(ms) npu1 延迟(ms) npu2
yolo26n-pose 19.542 11.446
yolo26s-pose 57.481 28.553

AX637

模型 延迟(ms)
yolo26n-pose 4.595
yolo26s-pose 11.848

使用方法

将此仓库中的所有文件下载到设备上

Python 环境要求

pyaxengine

https://github.com/AXERA-TECH/pyaxengine

wget https://github.com/AXERA-TECH/pyaxengine/releases/download/0.1.3.rc2/axengine-0.1.3-py3-none-any.whl
pip install axengine-0.1.3-py3-none-any.whl

其他

可能无。

在 AX650 主机上推理，例如 M4N-Dock(爱芯派Pro)

输入图像：

运行

python ax_infer_pose.py --model-path yolo26l-pose_npu3.axmodel --test-img bus.jpg

(ax_env) root@ax650:~/ax650# python ax_infer.py --model-path yolo26l-pose_npu3.axmodel --test-img bus.jpg
[INFO] Available providers:  ['AxEngineExecutionProvider']
[INFO] Using provider: AxEngineExecutionProvider
[INFO] Chip type: ChipType.MC50
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Engine version: 2.12.0s
[INFO] Model type: 2 (triple core)
[INFO] Compiler version: 5.1-patch1-dirty 9164b433-dirty
[YOLO26-Pose] [16:47:23.013] [DEBUG] Load model time = 838.91 ms
[YOLO26-Pose] [16:47:23.070] [DEBUG] Pre-process time = 16.87 ms
[YOLO26-Pose] [16:47:23.109] [DEBUG] Forward time = 39.14 ms
[YOLO26-Pose] [16:47:23.113] [DEBUG] Post-process time = 2.97 ms
[YOLO26-Pose] [16:47:23.117] [INFO] Draw Results (4 persons):
[YOLO26-Pose] [16:47:23.117] [INFO] (221, 406, 345, 859) -> person: 0.92
[YOLO26-Pose] [16:47:23.120] [INFO] (668, 391, 807, 880) -> person: 0.92
[YOLO26-Pose] [16:47:23.122] [INFO] (47, 397, 243, 901) -> person: 0.90
[YOLO26-Pose] [16:47:23.123] [INFO] (0, 439, 78, 949) -> person: 0.69
[YOLO26-Pose] [16:47:23.151] [INFO] Saved to result_yolo26_pose.jpg

输出图像：

AXERA-TECH/yolo26-pose

作者 AXERA-TECH

keypoint-detection
↓ 1 ♥ 0

创建时间: 2026-01-20 08:50:50+00:00

更新时间: 2026-01-26 01:51:04+00:00

在 Hugging Face 上查看

文件 (34)

.gitattributes
README.md
ax615/yolo26n-pose_npu1.axmodel
ax615/yolo26n-pose_npu2.axmodel
ax615/yolo26s-pose_npu1.axmodel
ax615/yolo26s-pose_npu2.axmodel
ax630C/yolo26n-pose_npu1.axmodel
ax630C/yolo26n-pose_npu2.axmodel
ax630C/yolo26s-pose_npu1.axmodel
ax630C/yolo26s-pose_npu2.axmodel
ax637/yolo26n-pose_npu1.axmodel
ax637/yolo26s-pose_npu1.axmodel
ax650/yolo26l-pose_npu1.axmodel
ax650/yolo26l-pose_npu3.axmodel
ax650/yolo26m-pose_npu1.axmodel
ax650/yolo26m-pose_npu3.axmodel
ax650/yolo26n-pose_npu1.axmodel
ax650/yolo26n-pose_npu3.axmodel
ax650/yolo26s-pose_npu1.axmodel
ax650/yolo26s-pose_npu3.axmodel
ax650/yolo26x-pose_npu1.axmodel
ax650/yolo26x-pose_npu3.axmodel
ax_infer.py
bus.jpg
coco_1000.tar
config.json
export_onnx.py
onnx_infer.py
result_yolo26_pose.jpg
yolo26l-pose_640x640.onnx ONNX
yolo26m-pose_640x640.onnx ONNX
yolo26n-pose_640x640.onnx ONNX
yolo26s-pose_640x640.onnx ONNX
yolo26x-pose_640x640.onnx ONNX