Skip to main content

Deploy YOLOv8 object detection model

This wiki will introduce how to train the official YOLOv8 target detection model and deploy the trained model to the Grove Vision AI (V2) device or XIAO ESP32S3 devices..

Dataset preparation​

It is recommended to use the roboflow platform for datasets. This platform can perform data set annotation and some data enhancement strategies, and supports the export of multiple data set formats.

Install YOLOv8 command line tool​

  • By default, you already have the python environment and pip package management tool, and python>=3.8.

Install the ultralytics package, or by running pip install -U ultralytics. Please visit the Python Package Index (PyPI) to learn more about the ultralytics package at https://pypi.org/project/ultralytics/.

# Install using pip
pip install ultralytics
# Chinese users can use mirror acceleration
# pip install ultralytics -i https://pypi.tuna.tsinghua.edu.cn/simple

Tips: If you are not familiar with the YOLOv8 code, it is recommended that you use pip or conda to install it.

  • You can use the version query command to test whether the yolo command line tool is successfully installed.
# version query
yolo -v

Train​

  • First, go to the downloaded data set folder

  • Execute the following command to start training the model

yolo train detect model=yolov8n.pt data=./data.yaml imgsz=192

Export model to tflite​

  • After training, the model will be in the runs/train/exp*/weights/ folder. Make sure that the evaluation indicators of your model meet your needs.
  • Use the following command to export the tflite model
yolo export model=${your model path}  format=tflite imgsz=192 int8
  • You will then see a yolov8n_saved_model folder under the current folder, which contains the yolov8n_full_integer_quant.tflite model file,This model file can be deployed to Grove Vision AI(V2) or XIAO ESP32S3 devices.

Model graph optimization​

  • Grove Vision AI (V2) supports vela-optimized models and can also accelerate model inference. First, execute the following command to install the vela command line tool (XIAO ESP32S3 device is not supported yet)

pip3 install ethos-u-vela
  • After that, you need to download vela related configuration file, or copy the following content into a file, which can be named vela_config.ini
; file: my_vela_cfg.ini ; ----------------------------------------------------------------------------- 
; Vela configuration file ; ----------------------------------------------------------------------------- 
; System Configuration 

; My_Sys_Cfg 
[System_Config.My_Sys_Cfg] 
core_clock=400e6 
axi0_port=Sram 
axi1_port=OffChipFlash 
Sram_clock_scale=1.0 
Sram_burst_length=32 
Sram_read_latency=16 
Sram_write_latency=16 
Dram_clock_scale=0.75 
Dram_burst_length=128 
Dram_read_latency=500 
Dram_write_latency=250 
OnChipFlash_clock_scale=0.25 
OffChipFlash_clock_scale=0.015625 
OffChipFlash_burst_length=32 
OffChipFlash_read_latency=64 
OffChipFlash_write_latency=64 
; ----------------------------------------------------------------------------- 
; Memory Mode 
; My_Mem_Mode_Parent 
[Memory_Mode.My_Mem_Mode_Parent] 
const_mem_area=Axi1 
arena_mem_area=Axi0 
cache_mem_area=Axi0
  • Finally, use the following command to optimize the graph
vela --accelerator-config ethos-u55-64 \ 
    --config vela_config.ini \
    --system-config My_Sys_Cfg \
    --memory-mode My_Mem_Mode_Parent \
    --output-dir ${Save path of the optimized model} \
    ${The path of the tflite model that needs to be optimized}

After execution, a graph-optimized tflite model will be generated in the path specified by --output-dir.

Deploy​

  • The model file that needs to be deployed is the tflite file exported above. You can burn the model file to the target device according to the following tutorial.

  • We strongly recommend using our web tool to burn the trained tflite model into the device. Detailed operations are provided in the Deployment Tutorial

Note: Since the ESP32S3 device does not support model deployment after vela graph optimization, you do not need to perform tflite model graph optimization if you want to deploy the model to the XIAO ESP32S3 device.

Loading Comments...