Skip to content

This project trains a YOLOv5 model for object detection and deploys it through a web interface. The web application is built using Flask for the backend and HTML/CSS/JavaScript for the frontend. Users can upload images to the website, and the model will detect objects and display the results on the same page.

Notifications You must be signed in to change notification settings

abhinavrajgupta/CleanScan-AI-Powered-Waste-Detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 

Repository files navigation

Author:

Abhinav Raj Gupta

Project File Descriptions

  1. Training/training.ipynb: Jupyter notebook containing all the training code for the YOLOv5 model. This includes data preprocessing, model configuration, training, and evaluation steps.

  2. Training/Requirements for virtual environment for training.txt: A text file listing all the required Python packages and dependencies needed to create a virtual environment for training the YOLOv5 model.

  3. Web/Requirements for virtual environment for web interface.txt: A text file listing all the required Python packages and dependencies to set up the Flask-based web interface.

  4. Web/Backend/app.py: Python script that runs the Flask backend for the web application. It handles image uploads, runs the YOLOv5 model for inference, and returns the detected results to the frontend.

  5. Web/Frontend/Static/index.css CSS file that styles: the frontend of the web application, providing layout, formatting, and visual enhancements for the image upload page.

  6. Web/Frontend/Static/index.js: JavaScript file that adds interactive functionality to the frontend, such as handling the image upload process and displaying results.

  7. Web/Frontend/Template/index.html: HTML file that structures the frontend of the web application. It contains the layout for the image upload form and the display of object detection results.

About

This project trains a YOLOv5 model for object detection and deploys it through a web interface. The web application is built using Flask for the backend and HTML/CSS/JavaScript for the frontend. Users can upload images to the website, and the model will detect objects and display the results on the same page.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published