This guide will provide instructions on how to convert OIDv4 data into the YOLO format for use with YOLOv8 object detection algorithms.
git clone https://github.com/prince0310/Men-wome-detection-using-yolov8-.git
Dataset
For training custom data set on yolo model you need to have data set arrangement in yolo format. which includes Images and Their annotation file.
git clone https://github.com/prince0310/OIDv4_ToolKit.git
it will create data in below format
Custom dataset
|
|─── train
| |
| └───Images --- 0fdea8a716155a8e.jpg
| └───Labels --- 0fdea8a716155a8e.txt
|
└─── test
| └───Images --- 0b6f22bf3b586889.jpg
| └───Labels --- 0b6f22bf3b586889.txt
|
└─── validation
| └───Images --- 0fdea8a716155a8e.jpg
| └───Labels --- 0fdea8a716155a8e.txt
|
└─── data.yaml
Install
Pip install the ultralytics package including all requirements.txt in a 3.10>=Python>=3.7 environment, including PyTorch>=1.7.
pip install ultralytics
Train
Python
from ultralytics import YOLO
# Train
model = YOLO("yolov8n.pt")
results = model.train(data="data.yaml", epochs=200, workers=1, batch=8,imgsz=640) # train the model
Cli
yolo detect train data=data.yaml model=yolov8n.pt epochs=200 imgsz=640
Detect
Python
from ultralytics import YOLO
# Load a model
model = YOLO("best.pt") # load a custom model
# Predict with the model
results = model("image.jpg", save = True) # predict on an image
Cli
yolo detect predict model=path/to/best.pt source="images.jpg" # predict with custom model