In this video, we'll show you how to quickly and easily train an object detection model on your own custom data using Yolov8. With just 10 minutes of your time, you'll learn how to set up your data, train the model, and evaluate its performance.

#ObjectDetection #YOLOv8 #CustomData #MachineLearning #DeepLearning #AI #ComputerVision #DataScience #TechTutorial #YoutubeTutorial #ObjectRecognition #NeuralNetworks #Python #AIProgramming #OpenCV #ImageProcessing #DataAnnotation #DeepLearningFramework #objecttracking

Note : Big thanks to roboflow blog and Piotr Skalski .


Code Snippet :

step1: CREATE YOUR CUSTOM DATASET USING ROBOFLOW

step2: IMPORT YOLOV8

!pip install ultralytics

#upload an image and check the installed package is working fine

yolo task=detect mode=predict model=yolov8n.pt conf=0.25 source=PATH O THE SAMPLE IMAGE

from IPython.display import Image


Image("PATH OF THE SAMPLE IMAGE", width=100, height=100)


step3: GET THE DATASET FROM ROBOFLOW


!pip install roboflow

from roboflow import Roboflow
rf = Roboflow(api_key="YOURAPIKEY")
project = rf.workspace("WORKSPACE").project("PROJECT")
dataset = project.version(1).download("yolov8")


step4: TRAIN THE MODEL


!yolo task=detect mode=train model=yolov8s.pt data={dataset.location}/data.yaml epochs=50 imgsz=640




step 5: TEST THE MODEL

!yolo task=detect mode=predict model=/content/runs/detect/train/weights/best.pt conf=0.25 source=PATH OF THE NEW TEST IMAGE


Image("PATH OF THE NEW TEST IMAGE", width=500, height=500)