metadata
license: agpl-3.0
language:
- en
base_model:
- YOLO26
pipeline_tag: object-detection
tags:
- WaveMatrix
- YOLO26
- NPU
- Ultralytics
YOLO26
This version of YOLOv26 has been converted to run on the WaveMatrix NPU using u8 (INT8) quantization.
Compatible with Pulsar2 version: 4.2.
Convert tools links:
For those who are interested in model conversion, you can try to export axmodel through
- The repo of WaveMatrix Platform, which you can get the detial of guide
- Pulsar2 Link, How to Convert ONNX to axmodel
Support Platform
- WM9955
- Demo board
- M.2 Accelerator card
- WM8845
- Demo board
Performance Statistics
WM9955 (NPU3 Mode)
| Model | FPS | CMM(MB) | Latency(ms) |
|---|---|---|---|
| yolo26n | 726 | 3.26 | 1.378 |
| yolo26s | 316 | 10.2 | 3.166 |
| yolo26m | 116 | 27.6 | 8.644 |
| yolo26l | 90 | 33.88 | 11.174 |
| yolo26x | 41.0 | 70.4 | 20.405 |
WM8845
| Model | Latency(ms) |
|---|---|
| yolo26n_npu1.axmodel | 10.706 |
| yolo26s_npu1.axmodel | 23.188 |
| yolo26n_npu2.axmodel | 6.309 |
| yolo26s_npu2.axmodel | 16.347 |
How to use
Download all files from this repository to the device
root@wm9955:~/YOLO26# tree .
|-- wm9955
| |-- yolo26n.axmodel
| |-- yolo26s.axmodel
| |-- yolo26m.axmodel
| |-- yolo26l.axmodel
| `-- yolo26x.axmodel
|-- wm8845c
| |-- yolo26n_npu1.axmodel
| |-- yolo26s_npu1.axmodel
| |-- yolo26n_npu2.axmodel
| |-- yolo26s_npu2.axmodel
|-- install_wm9955
| |-- ax_yolo26
|-- bus.jpg
|-- yolo26_out.jpg
Inference with wm9955 Host, such as demo board
(base) root@wm9955:~# ./ax_yolo26 -m ./wm9955/yolo26n.axmodel -i BUS.JPG
--------------------------------------
model file : ./wm9955/yolo26n.axmodel
image file : BUS.JPG
img_h, img_w : 640 640
--------------------------------------
Engine creating handle is done.
Engine creating context is done.
Engine get io info is done.
Engine alloc io is done.
Engine push input is done.
------------------------------------
Repeat 1 times, avg time 1.38 ms, max_time 1.38 ms, min_time 1.38 ms
--------------------------------------
detection num: 5
5: 94%, [ 6, 233, 801, 752], bus
0: 94%, [ 51, 396, 241, 904], person
0: 91%, [ 227, 406, 345, 861], person
0: 80%, [ 670, 389, 809, 876], person
0: 50%, [ 0, 556, 64, 872], person
--------------------------------------
Output image:
