Skip to content

Build an image classification model working with a real world dataset.

Notifications You must be signed in to change notification settings

opencodeiiita/Pestering-Data

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

50 Commits
 
 
 
 
 
 
 
 

Repository files navigation

🌿 Pestering-Data

Using Deep Learning to Classify Crop Health and Diseases


🚀 Overview

The use of Artificial Intelligence (AI) in agriculture has become increasingly prominent in recent years. AI in agriculture primarily aims to enhance crop productivity, manage pests and diseases, and reduce operational costs. In many developing countries, the agricultural sector faces significant challenges, including crop diseases and pest infestations, limited access to technological knowledge among farmers, and inadequate storage infrastructure, among other issues.

This project introduces a large-scale dataset comprising 22 classes divided into 4 main crops:

  • 🌰 Cashew
  • 🥔 Cassava
  • 🌽 Maize
  • 🍅 Tomato

Each category has further subdivisions:

  • Healthy classes
  • Disease-specific classes

🎯 Goal

Leverage modern Deep Learning techniques to create a model that accurately classifies crop images as either diseased or healthy.

📂 Dataset Structure:
Each crop folder contains:

  • train_set/ for training
  • test_set/ for testing

🔗 Dataset Link: Kaggle Dataset


📜 Instructions

  • Do not modify any pre-written code or comments.
  • Write your code only in the provided space.
  • Add meaningful comments to ensure smooth code reviews.
  • Create a Pull Request (PR) as per the issue guidelines.
  • Join the Discord server for any queries or clarifications.
  • Strictly refrain from any kind of plagiarism to avoid any sort of disqualification.

🔄 Procedure

  1. Download the dataset from the link provided above.
  2. Fork this repository and clone it to your local machine. (You may need to re-clone after each task.)
  3. Naming Conventions:
    • IIIT Allahabad Students: Name files as IIT2023098, where:
      • IIT = Your branch
      • 2023098 = Your unique ID
    • Other College Participants: Name files as COLLEGE_ROLLNO (e.g., IITBHU_123456).
  4. File Placement:
    • Push your .ipynb solution files to the correct folder:
      • Example: Place the solution for Task1 in Task1_solutions/.
  5. Submit a Pull Request:
    • Your PR will be reviewed by mentors.
    • Only relevant PRs will be merged and awarded points.

💡 Guidelines for Pull Requests

  • Follow the naming conventions strictly.
  • Use comments to explain your approach.
  • Push solutions to the correct folder only.

💬 Need Help?


🔧 Contribute, Collaborate, and Innovate! 🚀

Let’s make farming smarter with the power of AI and Deep Learning!