Making the YOLOv8 project more user-friendly with Streamlit .

Hello everyone! Today, I’ll explain how to make your YOLOv8 project more user-friendly by using the Streamlit library. With the Streamlit dashboard integrated with YOLOv8, you’ll be able to run object detection using external weight files and videos. Additionally, you’ll have the flexibility to change both the weight file and the detection location without closing the program. To get started, you’ll need to download the GitHub repository I’ve prepared [here]. <pre> git clone https://github.com/ilyasdemir-demirilyas/yolov8-streamlit-detection-tracking.git</pre> Once you’ve downloaded the repository, navigate to the project folder: <pre> cd yolov8-streamlit-detection-tracking</pre> You can now install the necessary libraries: <pre> pip install ultralytics streamlit pafy pip install pytube</pre> After completing all the preparations, you can run the code using the following command: <pre> streamlit run app.py</pre> dashboard : <ol> <li>image page:</li> </ol>   2. video page :   Simply running this command will take you into the dashboard. Now, let’s go through the steps to use YOLOv8 with the Streamlit dashboard: 1. Start by uploading the weight file with a .pt extension. 2. Next, choose the type and location of the object you want to detect (Image, Video, Webcam, etc.). 3. If you select video or image, upload the video or image you want to perform detection on. For YouTube videos, a link is sufficient. 4. Finally, for images, you can perform detection by simply selecting the confidence level and clicking the “Detect” button. For other options (relevant if you’re tracking), you can fine-tune the detection or tracking process by adjusting the confidence and IOU (Intersection over Union) values. If you have any questions or need further clarification on anything, please feel free to ask in the comments. Happy coding! <a href="https://medium.com/@ilyasdemir.demirilyas/making-the-yolov8-project-more-user-friendly-with-streamlit-ee2bde7affd8">Click Here</a>