AXERA-TECH/YOLO11-Seg

YOLO11-Seg

This version of YOLO11-Seg 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: 3.4

Convert tools links:

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

• The repo of AXera Platform, which you can get the detial of guide

• Pulsar2 Link, How to Convert ONNX to axmodel

Support Platform

• AX650
  • M4N-Dock(爱芯派Pro)
  • M.2 Accelerator card
• AX630C
  • 爱芯派2
  • Module-LLM
  • LLM630 Compute Kit

How to use

Download all files from this repository to the device

root@ax650:~/YOLO11-Pose# tree
.
|-- ax650
|   `-- yolo11x-seg.axmodel
|-- ax_yolo11_seg
|-- football.jpg
`-- yolo11_seg_out.jpg

Inference

Input image:

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

root@ax650:~/samples/AXERA-TECH/YOLO11-Seg# ./ax_yolo11_seg -m ax650/yolo11x-seg.axmodel -i football.jpg
--------------------------------------
model file : ax650/yolo11x-seg.axmodel
image file : football.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.
--------------------------------------

input size: 1
    name:   images [UINT8] [BGR]
        1 x 640 x 640 x 3

output size: 7
    name: /model.23/Concat_1_output_0 [FLOAT32]
        1 x 80 x 80 x 144

    name: /model.23/Concat_2_output_0 [FLOAT32]
        1 x 40 x 40 x 144

    name: /model.23/Concat_3_output_0 [FLOAT32]
        1 x 20 x 20 x 144

    name: /model.23/cv4.0/cv4.0.2/Conv_output_0 [FLOAT32]
        1 x 80 x 80 x 32

    name: /model.23/cv4.1/cv4.1.2/Conv_output_0 [FLOAT32]
        1 x 40 x 40 x 32

    name: /model.23/cv4.2/cv4.2.2/Conv_output_0 [FLOAT32]
        1 x 20 x 20 x 32

    name:  output1 [FLOAT32]
        1 x 32 x 160 x 160

post process cost time:16.90 ms
--------------------------------------
Repeat 1 times, avg time 34.59 ms, max_time 34.59 ms, min_time 34.59 ms
--------------------------------------
detection num: 9
 0:  94%, [ 757,  220, 1127, 1154], person
 0:  94%, [   0,  357,  314, 1112], person
 0:  93%, [1353,  339, 1629, 1037], person
 0:  91%, [ 494,  476,  659, 1001], person
32:  86%, [1231,  877, 1281,  922], sports ball
32:  73%, [ 774,  887,  828,  938], sports ball
32:  66%, [1012,  882, 1051,  927], sports ball
 0:  54%, [   0,  543,   83, 1000], person
 0:  46%, [1837,  696, 1877,  814], person
--------------------------------------

Output image:

Inference with M.2 Accelerator card

(base) axera@raspberrypi:~/lhj/YOLO11-Seg $ ./axcl_aarch64/axcl_yolo11_seg -m ax650/yolo11x-seg.axmodel -i football.jpg 
--------------------------------------
model file : ax650/yolo11x-seg.axmodel
image file : football.jpg
img_h, img_w : 640 640
--------------------------------------
axclrtEngineCreateContextt is done. 
axclrtEngineGetIOInfo is done. 

grpid: 0

input size: 1
    name:   images 
        1 x 640 x 640 x 3

output size: 7
    name: /model.23/Concat_1_output_0 
        1 x 80 x 80 x 144

    name: /model.23/Concat_2_output_0 
        1 x 40 x 40 x 144

    name: /model.23/Concat_3_output_0 
        1 x 20 x 20 x 144

    name: /model.23/cv4.0/cv4.0.2/Conv_output_0 
        1 x 80 x 80 x 32

    name: /model.23/cv4.1/cv4.1.2/Conv_output_0 
        1 x 40 x 40 x 32

    name: /model.23/cv4.2/cv4.2.2/Conv_output_0 
        1 x 20 x 20 x 32

    name:  output1 
        1 x 32 x 160 x 160

==================================================

Engine push input is done. 
--------------------------------------
post process cost time:3.47 ms 
--------------------------------------
Repeat 1 times, avg time 34.89 ms, max_time 34.89 ms, min_time 34.89 ms
--------------------------------------
detection num: 9
 0:  94%, [ 757,  220, 1127, 1154], person
 0:  94%, [   0,  357,  314, 1112], person
 0:  93%, [1353,  339, 1629, 1037], person
 0:  91%, [ 494,  476,  659, 1001], person
32:  86%, [1231,  877, 1281,  922], sports ball
32:  73%, [ 774,  887,  828,  938], sports ball
32:  66%, [1012,  882, 1051,  927], sports ball
 0:  54%, [   0,  543,   83, 1000], person
 0:  46%, [1837,  696, 1877,  814], person
--------------------------------------

Output image: