Tutorial Lengkap Ultralytics: Object Detection dengan YOLO

Ultralytics adalah framework Python yang menyediakan implementasi state-of-the-art untuk YOLO (You Only Look Once), salah satu algoritma object detection paling populer dan efisien. Dalam tutorial ini, kita akan mempelajari cara menggunakan Ultralytics dari instalasi hingga deployment model custom.

Apa itu Ultralytics dan YOLO?

YOLO adalah algoritma real-time object detection yang dapat mendeteksi multiple objects dalam satu forward pass neural network. Ultralytics menyediakan implementasi YOLOv8, YOLOv9, YOLOv10, dan YOLO11 yang mudah digunakan dengan performa tinggi.

• API yang sangat sederhana dan intuitif
• Support multiple tasks: detection, segmentation, classification, pose estimation
• Pretrained models untuk berbagai use case
• Easy training dan finetuning
• Export ke berbagai format (ONNX, TensorRT, CoreML, dll)

Instalasi

1. Setup Environment

# Buat virtual environment
python -m venv ultralyticsenv

source ultralyticsenv/bin/activate  # Linux/Mac
ultralyticsenv\Scripts\activate  # Windows


Install Ultralytics
pip install ultralytics

Untuk GPU support (CUDA)
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu118

import ultralytics
from ultralytics import YOLO

Check version
print(f"Ultralytics version: {ultralytics.version}")

Check CUDA availability
import torch
print(f"CUDA available: {torch.cuda.isavailable()}")
if torch.cuda.isavailable():

    print(f"GPU: {torch.cuda.getdevicename(0)}")

from ultralytics import YOLO

Load model YOLOv8 (tersedia: yolov8n, yolov8s, yolov8m, yolov8l, yolov8x)
n=nano, s=small, m=medium, l=large, x=extra large
model = YOLO('yolov8n.pt')  # Model otomatis di-download

Atau load YOLO11 (terbaru)
model = YOLO('yolo11n.pt')

from ultralytics import YOLO

Load model
model = YOLO('yolov8n.pt')

Inference pada single image
results = model('path/to/image.jpg')

Inference pada multiple images
results = model(['image1.jpg', 'image2.jpg', 'image3.jpg'])

Inference dari URL
results = model('https://example.com/image.jpg')

Process results
for result in results:
    # Bounding boxes
    boxes = result.boxes
    print(f"Detected {len(boxes)} objects")

    for box in boxes:
        # Koordinat box (x1, y1, x2, y2)
        xyxy = box.xyxy[0].tolist()

        # Confidence score
        confidence = box.conf[0].item()

        # Class ID dan nama
        classid = int(box.cls[0].item())
        classname = model.names[classid]

        print(f"  {classname}: {confidence:.2f} at {xyxy}")

from ultralytics import YOLO
import cv2

model = YOLO('yolov8n.pt')

Inference pada video file
results = model('path/to/video.mp4', stream=True)

for result in results:
    # Process setiap frame
    annotatedframe = result.plot()

    # Display (optional)
    cv2.imshow('Detection', annotatedframe)

    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

cv2.destroyAllWindows()

from ultralytics import YOLO
import cv2

model = YOLO('yolov8n.pt')

Open webcam
cap = cv2.VideoCapture(0)

while cap.isOpened():
    ret, frame = cap.read()
    if not ret:
        break

    # Run inference
    results = model(frame, verbose=False)