YOLO11

For a detailed process of model export, quantization, and compilation based on the Ultralytics YOLO11 series models, please refer to Deploying YOLO11 on AX650N

Download the integration package and upload it to the Raspberry Pi, or execute the following commands in the Raspberry Pi terminal.

Download

wget https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/linux/ax8850_card/axcl_demo.zip

Unzip

unzip axcl_demo.zip

YOLO11x

Run:

./axcl_demo/axcl_yolo11 -i axcl_demo/ssd_horse.jpg -m axcl_demo/yolo11x.axmodel

The running result is as follows:

m5stack@raspberrypi:~/rsp $ ./axcl_demo/axcl_yolo11 -i axcl_demo/ssd_horse.jpg -m axcl_demo/yolo11x.axmodel
--------------------------------------
model file : axcl_demo/yolo11x.axmodel
image file : axcl_demo/ssd_horse.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: 3
    name: /model.23/Concat_output_0
        1 x 80 x 80 x 144

    name: /model.23/Concat_1_output_0
        1 x 40 x 40 x 144

    name: /model.23/Concat_2_output_0
        1 x 20 x 20 x 144

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

Engine push input is done.
--------------------------------------
post process cost time:0.88 ms
--------------------------------------
Repeat 1 times, avg time 24.69 ms, max_time 24.69 ms, min_time 24.69 ms
--------------------------------------
detection num: 6
17:  96%, [ 216,   71,  423,  370], horse
16:  93%, [ 144,  203,  196,  345], dog
 0:  89%, [ 273,   14,  349,  231], person
 2:  88%, [   1,  105,  132,  197], car
 0:  82%, [ 431,  124,  451,  178], person
19:  46%, [ 171,  137,  202,  169], cow
-------------------------------------- 

YOLO11x-Seg

Run:

./axcl_demo/axcl_yolo11_seg -i axcl_demo/ssd_horse.jpg -m axcl_demo/yolo11x-seg.axmodel

The running result is as follows:

m5stack@raspberrypi:~/rsp $ ./axcl_demo/axcl_yolo11_seg -i axcl_demo/ssd_horse.jpg -m axcl_demo/yolo11x-seg.axmodel
--------------------------------------
model file : axcl_demo/yolo11x-seg.axmodel
image file : axcl_demo/ssd_horse.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:5.62 ms
--------------------------------------
Repeat 1 times, avg time 34.72 ms, max_time 34.72 ms, min_time 34.72 ms
--------------------------------------
detection num: 6
17:  96%, [ 216,   71,  423,  370], horse
16:  93%, [ 144,  203,  196,  345], dog
 0:  89%, [ 273,   14,  349,  231], person
 2:  88%, [   1,  105,  132,  197], car
 0:  82%, [ 431,  124,  451,  178], person
19:  46%, [ 171,  137,  202,  169], cow
-------------------------------------- 

YOLO11x-Pose

Run:

./axcl_demo/axcl_yolo11_pose -i axcl_demo/football.jpg -m axcl_demo/yolo11x-pose.axmodel

The running result is as follows:

m5stack@raspberrypi:~/rsp $ ./axcl_demo/axcl_yolo11_pose -i axcl_demo/football.jpg -m axcl_demo/yolo11x-pose.axmodel
--------------------------------------
model file : axcl_demo/yolo11x-pose.axmodel
image file : axcl_demo/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: 6
    name: /model.23/Concat_1_output_0
        1 x 80 x 80 x 65

    name: /model.23/Concat_2_output_0
        1 x 40 x 40 x 65

    name: /model.23/Concat_3_output_0
        1 x 20 x 20 x 65

    name: /model.23/cv4.0/cv4.0.2/Conv_output_0
        1 x 80 x 80 x 51

    name: /model.23/cv4.1/cv4.1.2/Conv_output_0
        1 x 40 x 40 x 51

    name: /model.23/cv4.2/cv4.2.2/Conv_output_0
        1 x 20 x 20 x 51

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

Engine push input is done.
--------------------------------------
post process cost time:0.36 ms
--------------------------------------
Repeat 1 times, avg time 25.09 ms, max_time 25.09 ms, min_time 25.09 ms
--------------------------------------
detection num: 6
 0:  94%, [1350,  337, 1632, 1036], person
 0:  93%, [ 492,  477,  658, 1000], person
 0:  92%, [ 756,  219, 1126, 1154], person
 0:  91%, [   0,  354,  314, 1108], person
 0:  73%, [   0,  530,   81, 1017], person
 0:  54%, [ 142,  589,  239, 1013], person
-------------------------------------- 

Next Overview

Linux PC

CM4Stack

CoreMP135

AI Accelerator Card

LLM-8850 Card

Quick Start

Vision Models

Large Language Models

Multimodal Models

Audio Models

Generative Models

Advanced Usage

LLM

Real-Time AI Voice Assistant

OpenAI Voice Assistant

XiaoZhi Voice Assistant

XiaoLing Voice Assistant

AtomS3R-M12 Volcengine Kit

Offline Voice Recognition

Unit ASR

Home Assistant

Industrial Control

StamPLC

IoT Measuring Instruments

Air Quality

Module13.2 PPS

VAMeter

T-Lite

Ezdata

Ethernet Camera

PoECAM

Wi-Fi Camera

TimerCAM

Unit CamS3/-5MP

AI Camera

UnitV2

M5StickV/UnitV

LoRa & LoRaWAN

TTN (The Things Network)

Meshtastic

Motor Control

Unit Roller485/CAN

Develop Tools

Hobby Kit

Restore Factory Firmware