YOLOv8 Streamlit APP

Introduction

This repository supply a user-friendly interactive interface for YOLOv8 and the interface is powered by Streamlit. It could serve as a resource for future reference while working on your own projects.

Features

Feature1: Object detection task.
Feature2: Multiple detection models. yolov8n, yolov8s, yolov8m, yolov8l, yolov8x
Feature3: Multiple input formats. Image, Video, Webcam

Interactive Interface

Image Input Interface

Video Input Interface

Webcam Input Interface

Installation

Create a new conda environment

# create
conda create -n yolov8-streamlit python=3.8 -y

# activate
conda activate yolov8-streamlit

Clone repository

git clone https://github.com/JackDance/YOLOv8-streamlit-app

Install packages

# yolov8 dependencies
pip install ultralytics

# Streamlit dependencies
pip install streamlit

Download Pre-trained YOLOv8 Detection Weights

Create a directory named weights and create a subdirectory named detection and save the downloaded YOLOv8 object detection weights inside this directory. The weight files can be downloaded from the table below.

Model	size ^(pixels)	mAP^val 50-95	Speed ^{CPU ONNX (ms)}	Speed ^{A100 TensorRT (ms)}	params ^(M)	FLOPs ^(B)
YOLOv8n	640	37.3	80.4	0.99	3.2	8.7
YOLOv8s	640	44.9	128.4	1.20	11.2	28.6
YOLOv8m	640	50.2	234.7	1.83	25.9	78.9
YOLOv8l	640	52.9	375.2	2.39	43.7	165.2
YOLOv8x	640	53.9	479.1	3.53	68.2	257.8

Run

streamlit run app.py

Then will start the Streamlit server and open your web browser to the default Streamlit page automatically.

TODO List

Add Tracking capability.
Add Classification capability.
Add Pose estimation capability.

If you also like this project, you may wish to give a star (^.^)✨ . If any questions, please raise issue~