How To Train YOLOv8.1-OBB (Oriented Bounding Boxes) custom object detection tutorial

preview_player
Показать описание
n this tutorial, you'll learn how to create a custom object detection Oriented bounding box model using YOLOv8.1.
Oriented bounding boxes are bounding boxes rotated to better fit the objects represented on an angle.
Using YOLOv8.1-obb we are able to detect objects that are rotated on a given frame or image more tightly and accurately.

00:00 - intro
0:50 - what is OBB
0:58 - Alima Open AI API Template
1:31 - Label Format
2:36 - Dataset
3:26 - Google Collab Setup
4:19 - Roboflow Login
5:50 - Dataset Format
8:29 - Train the model
9:52 - Evaluate the model
10:08 - Download Video
10:43 - Predict Images
12:07 - Predict Video
13:35 - Change Format

_______________________________________________________________

💷 50% Discount Code : A2LH6LZ

_______________________________________________________________

Tags:
#obb #objectdetection #yolov8 #ultralytics #yolo #roboflow
Рекомендации по теме
Комментарии
Автор

Can you tell me how the yolov8 architecture works? I would like to ask how to train the model to recognize circles and output, instead of the width and height of the bounding quadrangle, the x/y location and radius.

raphaild
Автор

very nice and to the point like always. Keep it up bro 🔥

SiaTheWizard