Downloads · 30 days
201
15% of all-time downloads
YOLOv8-Pose
AXERA-TECH/YOLOv8-Pose
YOLOv8-Pose is a object detection model from AXERA-TECH. Use it when you need objects located in an image. The card lists the license as mit.
This version of YOLOv8-POSE has been converted to run on the Axera NPU using w8a16 quantization.
All-time downloads
1.3K
Public
Repo size
2.1 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.axmodel917 MB · 54%
At a glance
- Task
- Object Detection
- License
- mit
- Model type
- ONNX
- Access
- Public
- Created
- Nov 25, 2025
- Updated
- Jul 31, 2026
- SHA
- f8bd38d5
Base models
Model card
From the Hugging Face model README
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
Support Platform
- AX650N/AX8850
- AX630C
- 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:
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:
- Task
- Object Detection
- Type
- ONNX
- License
- mit
- Languages
- en
- Created
- Nov 25, 2025
- Updated
- Jul 31, 2026