Tutorial: Yolov8 in PyTorch
Tutorial: YOLO v8 in PyTorch
https://docs.ultralytics.com/quickstart/#install-ultralytics
Ultralytics YOLOv8 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
Documentation and Github
See the YOLOv8 Docs for full documentation on training, validation, prediction and deployment.
Also, you can visit the github repository: https://github.com/ultralytics/ultralytics
Installation of Yolov8
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
For installations of requirements, read for more detail instructions
Python >=3.8
PyTorch>=1.8
opencv-python>=4.6.0
matplotlib>=3.3.0
and more. See requirements
Install Yolov8 via pip package
First, create a new environment for YOLOv8 in Anaconda Prompt.
e.g. $myENV$ = yolov8
You can also make an exact copy of the existing environment by creating a clone
If you already have an environment named
py39
, clone it asyolov8
Activate the environment and Install YOLOv8 with pip to get stable packages.
Also, install the latest ONNX
Check for YOLO Installation
After the installation, you can check the saved source code and libs of YOLOv8 in the local folder :
\USER\anaconda3\envs\yolov8\Lib\site-packages\ultralytics
Now, lets run simple prediction examples to check the YOLO installation.
In Anaconda Prompt, activate yolov8
environment.
Then, move directory to the working directory. Here, the result images will be saved.
Example:
C:\Users\ykkim\source\repos\DLIP\yolov8\
Run a Detection Example
In the Anaconda prompt, type the following command to predict a simple image.
The result will be saved in the project folder \runs\detect\predict\
Example: C:\Users\ykkim\source\repos\DLIP\yolov8\runs\detect\predict\
Run a Segmentation Example
Predict a YouTube video using a pretrained segmentation model at image size 320:
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
Example: Detection Inference
Read Doc of Prediction with YOLO for more examples
Download the dataset file and save in the project folder
You can download the COCO pretrained models such as YOLOv8n and more.
https://docs.ultralytics.com/datasets/detect/coco/
Inference one image
Create a new python source file in the project folder
Yolo8-Inference-Ex1.py
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
.
Inference on Webcam stream
Create a new python source file in the project folder
Yolo8-Inference-Webcam-Ex3.py
Example: Train
Last updated