nimrodzw/AgriShield

"AgriShield" is an AI/ML-based solution designed to leverage the power of 5G/6G networks to enhance agricultural resilience in Zimbabwe and across Africa. Our solution provides real-time crop monitoring, predictive analytics for weather and pest outbreaks, and an AI-driven marketplace that optimizes farm-to-market logistics. # 🌱 **AgriShield** - AI Powered Agriculture Insights 🌾 Welcome to **AI-Powered Agriculture Insights**, a cutting-edge solution that leverages AI and Machine Learning models to detect **leaf diseases**, **pests**, and **cell towers** through image recognition. This project combines three powerful models to help farmers and agronomists make data-driven decisions, all in real-time. ## 🚀 Project Overview This repository contains code for utilizing **Roboflow’s inference API** to analyze images and detect potential issues in agriculture, such as: - **Leaf Diseases** (leaf-disease-nsdsr model) - **Pests** (pests-2xlvx model) - **Cell Towers** (cell-towers model) Each image is processed and results are presented in a **cool, well-formatted HTML report**. This project is designed with modularity in mind, with each dataset API in separate Python files, all working together to create a seamless user experience. --- ## 📂 Project Structure ```bash ├── dataset_api_1.py # Leaf Disease Detection using the API ├── dataset_api_2.py # Pests Detection using the API ├── dataset_api_3.py # Cell Towers Detection using the API ├── generate_report.py # Generates the HTML report with all results ├── results/ # Folder to store generated HTML reports └── README.md # This awesome README file ``` ## ⚙️ Setup Instructions 1. **Clone the repository**: ```bash git clone github.com cd AgriShield ``` 2. **Install dependencies**: Ensure you have `inference_sdk` installed: ```bash pip install inference_sdk ``` 3. **Add Your Images**: Replace the placeholder `your_image.jpg` in the script with the path to your image for each dataset. --- ## 💻 How to Run Once everything is set up, you can run the detection process using the following steps: 2. **Run Main.py**: Generate the HTML report: Generate a consolidated HTML report with the results: ```bash python main.py ``` The results will be sto …