YOLOv8 model deployment based on AidLux
This article will introduce the content from three aspects: AidLux introduction, YOLOv8 model conversion, and YOLOv8 model deployment.
Introduction, installation and environment configuration of AidLux Introduction, installation and environment configuration of AidLux
Introduction of AidLux
AidLux is a fusion architecture platform independently developed by Chengdu Ajiaxi Intelligent Technology Co., Ltd. It provides an Android/Hongmeng+Linux fusion system. The dual systems can be used independently and communicate with each other.
Ajiaxi is committed to the continuous innovation of artificial intelligence core technology, creating an original integrated architecture operating system to meet the needs of various application scenarios, providing an out-of-the-box AI tool chain to make it easier to use chip computing power, and realizing the rapid migration and implementation of AIoT projects. Comprehensively assist enterprises in industrial intelligence, AI education, robotics, smart home and other fields to achieve rapid product iteration and intelligent upgrade.
AidLux installation and environment configuration
installation steps:
- Download and install the AidLux application from the Android mobile app market. The installation package size is 1.2g
- Open AidLux, configure various permissions, mobile phone-Settings-About mobile phone-click the system version number multiple times to open developer mode
- Restart AidLux and choose to log in or log in without registration. When the application system is opened for the first time, AidLux needs to be loaded and wait for the progress bar to complete.
- After entering the AidLux interface on the mobile phone, check the Cloud_ip blue cloud icon on the desktop of the mobile phone to obtain the IP and port number.
- Enter the IP address and port number in the PC browser. The login interface is the root user. Enter aidlux (default password) to log in to the AidLux desktop.
- Enter the IP address and port number in the PC browser. The login interface is the root user. Enter aidlux (default password) to log in to the AidLux desktop.
Update mirror source: pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
Update pip: /usr/loacl/bin/python3 -m pip install --upgrade pip
installs the required tools Package: pip install numpy opencv-python
Install vscode:
- Open the application center and select Linux-Aid source-vscode to install
- Enter Installed-Click vscode-Click Add to Desktop-Display vscode on the desktop
- Enter Installed-Click vscode-Click Add to Desktop-Display vscode on the desktop
YOLOv8 model conversion
First, convert our trained YOLOv8 model to onnx format, and then convert it to tflite format, or convert it to dlc format.
from ultralytics import YOLO
# Load a model
model = YOLO("yolov8n.yaml") # build a new model from scratch
model = YOLO("yolov8n.pt") # load a pretrained model (recommended for training)
# Use the model
path = model.export(format="onnx") # export the model to ONNX format
path = model.export(format="tflite") # export the model to tflite format
YOLOv8 model deployment based on tflite
DLC-based yolov8 model deployment
detection video
Attached here is the link to the detection video:
Detection video