UltralyticsYOLOv8 is a cutting-edge, state-of-the-art (SOTA) model that builds upon the success of previous YOLO versions and introduces new features and improvements to further boost performance and flexibility. Y
img
Documentation and Github
See the YOLOv8 Docs for full documentation on training, validation, prediction and deployment.
Ultralytics provides various installation methods including pip, conda, and Docker. Install YOLOv8 via the ultralytics pip package for the latest stable release or by cloning the Ultralytics GitHub repository for the most up-to-date version.
Requirement
Install necessary packages such as Python, Numpy, PyTorch, CUDA and more
The result will be saved in the project folder \runs\segment\predict\
Using YOLOv8 with Python : Example Codes
In the project folder, create a new python code file
Project Folder: \source\repos\DLIP\yolov8\
Activate yolov8 environment in Anaconda Prompt
A list of useful commands for YOLOv8
from ultralytics import YOLO# Create a new YOLO model from scratchmodel =YOLO('yolov8n.yaml')# Load a pretrained YOLO model (recommended for training)model =YOLO('yolov8n.pt')# Train the model using the 'coco8.yaml' dataset for 3 epochsresults = model.train(data='coco8.yaml', epochs=3)# Evaluate the model's performance on the validation setresults = model.val()# Perform object detection on an image using the modelresults =model('https://ultralytics.com/images/bus.jpg')
Create a new python source file in the project folder
Yolo8-Inference-Ex1.py
########################################################## YOLO v8 Tutorial : Prediction Ex1## Load Pretrained Model and Display the Annoted Results##########################################################from ultralytics import YOLOimport cv2from matplotlib import pyplot as plt# Load a pretrained YOLO model (recommended for training)model =YOLO('yolov8n.pt')# Inference Source - a single sourcesrc = cv2.imread("bus.jpg")# Perform object detection on an image using the modelresult = model.predict(source=src, save=True, save_txt=True)# save predictions as labels# View result for r in result:# print the Boxes object containing the detection bounding boxes print(r.boxes)# Show results to screen (not recommended)print("result.show()") r.show()# Plot results image print("result.plot()") dst = r.plot()# return BGR-order numpy array cv2.imshow("result plot",dst)# Plot the original image (NParray)print("result.orig_img") cv2.imshow("result orig",r.orig_img)# Save results to diskr.save(filename='result.jpg')cv2.waitKey(0)##########################################################################################
Inference of multiple images
Create a new python source file in the project folder
Yolo8-Inference-Ex2.py
For multiple input source images, you can copy bus.jpg as bus2.jpg.
########################################################## YOLO v8 Tutorial : Prediction Ex2## Load Pretrained Model and Display the Annoted Results (multiple images)##########################################################from ultralytics import YOLOimport cv2from matplotlib import pyplot as plt# Load a pretrained YOLO model (recommended for training)model =YOLO('yolov8n.pt')# Inference Source - multiple images# Perform object detection on images using the modelresults =model(['bus.jpg', 'bus2.jpg'])# return a list of Results objects# View resultsfor i, r inenumerate(results):# Plot results image dst = r.plot()# return BGR-order numpy array cv2.imshow("r.plot",dst)# Save results to disk r.save(filename=f'results{i}.jpg')cv2.waitKey(0)
Inference on Webcam stream
Create a new python source file in the project folder
Yolo8-Inference-Webcam-Ex3.py
########################################################## YOLO v8 Tutorial : Prediction Ex3## Stream Video Prediction ## This script will run predictions on each frame of the video# visualize the results, and display them in a window. # The loop can be exited by pressing 'q'.#########################################################import cv2 as cvfrom ultralytics import YOLO# Load the YOLOv8 modelmodel =YOLO('yolov8n.pt')# Open the video camera no.0cap = cv.VideoCapture(0)# If not success, exit the programifnot cap.isOpened():print('Cannot open camera')# Loop through the video frameswhile cap.isOpened():# Read a frame from the video success, frame = cap.read()if success:# Run YOLOv8 inference on the frame results =model(frame)# Visualize the results on the frame annotated_frame = results[0].plot()# Display the annotated frame cv.imshow("YOLOv8 Inference", annotated_frame)# Break the loop if 'q' is pressedif cv.waitKey(1)&0xFF==ord("q"):breakelse:# Break the loop if the end of the video is reachedbreak# Release the video capture object and close the display windowcap.release()cv.destroyAllWindows()
