Scribd
Upload
79 views2 pages

Object Detection Using Yolov8 On A Custom Dataset

The document outlines the implementation and training of a YOLOv8 model for object detection on a custom dataset, detailing steps such as data preparation, model selection, training, and evaluation. It emphasizes the model's ability to accurately detect and localize objects in images, showcasing its effectiveness in real-time tasks. The process includes configuring datasets, training with specified parameters, and analyzing performance metrics.

Uploaded by

arasupadhmasini
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
79 views2 pages

Object Detection Using Yolov8 On A Custom Dataset

The document outlines the implementation and training of a YOLOv8 model for object detection on a custom dataset, detailing steps such as data preparation, model selection, training, and evaluation. It emphasizes the model's ability to accurately detect and localize objects in images, showcasing its effectiveness in real-time tasks. The process includes configuring datasets, training with specified parameters, and analyzing performance metrics.

Uploaded by

arasupadhmasini
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

OBJECT DETECTION USING YOLOV8 ON A CUSTOM DATASET

EX : 6
DATE : 8/7/25

AIM
To implement and train a YOLOv8 model for object detection on a custom
dataset, enabling the accurate identification and localization of objects within
images.

ALGORITHM (YOLOV8-BASED OBJECT DETECTION)


1. Data Preparation
o Organize images into train, val, and optionally test directories.

o Provide corresponding label files in YOLO format under labels/.

2. Configure Dataset
o Create [Link] specifying class names and dataset paths.

3. Model Selection
o Choose a YOLOv8 variant (e.g., [Link], [Link], etc.) based
on performance vs. speed trade-offs.
4. Training
o Train the model using:

o yolo task=detect mode=train model=[Link] data=[Link]


epochs=50 imgsz=640
5. Prediction/Inference
o Predict on new or validation images:

o yolo task=detect mode=predict


model=runs/detect/train6/weights/[Link]
source=dataset/images/val
6. Evaluation
o Analyze metrics like precision, recall, and mAP in the training
summary and visual outputs.

INFERENCE
The trained YOLOv8 model successfully detects and localizes objects in unseen
images from the validation set. Bounding boxes are accurately drawn with
confidence scores, indicating the model’s reliability in identifying objects as
trained. The results demonstrate the effectiveness of YOLOv8 in real-time object
detection tasks on custom datasets.
OUTPUT :

You might also like