Modelpublic

AXERA-TECH/YOLOv8-Pose

sourceHugging Facemitupdated 2mo agoView on Hugging Face

1likes233downloads

Model Card

YOLOv8-POSE

This version of YOLOv8-POSE has been converted to run on the Axera NPU using w8a16 quantization.

This model has been optimized with the following LoRA:

Compatible with Pulsar2 version: 5.0

Convert tools links:

For those who are interested in model conversion, you can try to export axmodel through

—The repo of ax-samples, which you can get the how to build the ax_yolov8_pose

—The repo of axcl-samples, which you can get the how to build the axcl_yolov8_pose

—Pulsar2 Link, How to Convert ONNX to axmodel

Support Platform

—AX650N/AX8850
—M4N-Dock(爱芯派Pro)
—M.2 Accelerator card
—AX630C
—爱芯派2
—Module-LLM
—LLM630 Compute Kit
—AX615
—AX637

Performance Statistics

AX650N

Model	Latency(ms) npu1	Latency(ms) npu3
yolov8n-pose	4.135	1.453
yolov8s-pose	10.842	3.764
yolov8m-pose	27.515	9.577
yolov8l-pose	52.560	18.221
yolov8x-pose	90.257	29.313

AX630C

Model	Latency(ms) npu1	Latency(ms) npu2
yolov8n-pose	14.738	8.213
yolov8s-pose	33.157	24.109
yolov8m-pose	82.267	57.532
yolov8l-pose	145.686	101.811
yolov8x-pose	248.331	160.857

AX615

Model	Latency(ms) npu1	Latency(ms) npu2
yolov8n-pose	17.402	10.083
yolov8s-pose	50.240	28.091
yolov8m-pose	136.386	70.737

AX637

Model	Latency(ms) npu1
yolov8n-pose	4.838
yolov8s-pose	12.250
yolov8m-pose	28.938
yolov8l-pose	55.146
yolov8x-pose	86.095

How to use

Download all files from this repository to the device

Inference

Input image: [image]

Inference with AX650 Host, such as M4N-Dock(爱芯派Pro)

(base) root@ax650:~/ax650pose# python3 ax_infer.py --model-path yolov8s-pose_640x640_npu3.axmodel --test-img bus.jpg
[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: 6.0 a498e20d
[YOLOv8-Pose] [15:35:43.230] [DEBUG] Load model time = 576.32 ms
[YOLOv8-Pose] [15:35:43.301] [DEBUG] Pre-process time = 21.58 ms
[YOLOv8-Pose] [15:35:43.328] [DEBUG] Forward time = 26.25 ms
[YOLOv8-Pose] [15:35:43.335] [DEBUG] Post-process time = 6.46 ms
[YOLOv8-Pose] [15:35:43.341] [INFO] Draw Results (4 persons):
[YOLOv8-Pose] [15:35:43.342] [INFO] (222, 404, 344, 859) -> person: 0.89
[YOLOv8-Pose] [15:35:43.347] [INFO] (49, 397, 244, 902) -> person: 0.88
[YOLOv8-Pose] [15:35:43.348] [INFO] (669, 392, 808, 875) -> person: 0.87
[YOLOv8-Pose] [15:35:43.349] [INFO] (0, 413, 78, 935) -> person: 0.57
[YOLOv8-Pose] [15:35:43.377] [INFO] Saved to result_yolov8_pose.jpg

Output image: [image]