PlantAi is a ResNet-based CNN model trained on the PlantVillage dataset to classify plant leaf images as healthy or diseased. This repository includes PyTorch training code, tools to convert the model to TensorFlow Lite (TFLite) for deployment, and an Android app integrating the model for real-time leaf disease detection from camera images.

First Open Nepal-Specific Agricultural AI Dataset & Model

Deep learning solution for apple disease detection using CNN architecture. Trained on PlantVillage dataset to classify 4 apple leaf conditions with real-time image analysis.

MangoMediX 🌿 – AI-powered mango leaf disease prediction system using ResNet50, Flask, and a user-friendly web interface. Detects 8 mango leaf diseases with 92% accuracy and provides treatment suggestions.

Deep Learning Project for Sugarcane Disease Prediction and Classification Using CNN Architectures

GreenFund is an AI-powered web application that empowers farmers to make data-driven, climate-smart agricultural decisions. The platform focuses on analysis of soil health then additionally tracks farm activities, measures carbon emissions, and provides AI-driven crop recommendations to promote sustainable and climate-resilient farming.

AI-powered smart farming system for crop yield & price prediction, nutrient optimization with what-if analysis, and CV-based deficiency detection

Data augmentation framework and convolutional neural network for classification of cassava crop diseases from leaf images 🌱

🌱 AI-powered crop disease detection app for farmers. Identify plant diseases, get treatment recommendations, and connect with the farming community using React Native.

AI-powered web application for real-time plant leaf disease detection using a fine-tuned ResNet-34 CNN, built with PyTorch and Flask.

End-to-end deep learning system for sugarcane leaf disease detection using PyTorch, ResNet-50, FastAPI, and Docker.

Hyperparameter-tuned Xception model for plant disease detection with 97.23% accuracy – published at IEEE ICAIQSA 2024

Automated cattle body condition scoring system using YOLOv8, OpenCV and Flask. 🐄 Detects cattle, segments the body, extracts geometric features and generates body, height and rump condition scores with annotated outputs. Prototype built for Smart India Hackathon. 🚀

Deep learning model for detecting plant diseases using CNN and Streamlit.

A data-driven fruit shelf life prediction system using computer vision and statistical modeling. The project analyzes aroma decay patterns and visual features to estimate spoilage timelines and optimize post-harvest storage and supply chain decisions.

Systematic optimization of MobileNetV2 for citrus plant disease detection. Includes 18+ detailed experiments on hyperparameters, augmentations, and fine-tuning. Part of the Agro-AI project for Teknofest 2026.

🚀 A scalable Python backend for an AI chatbot built for agriculture and aquaculture. It delivers real-time insights on crops, pest detection, and fish farming. With secure APIs and modular design, it integrates seamlessly into apps, empowering farmers 🌱 and businesses to boost productivity, efficiency, and sustainability.

Deep learning–based system to detect and classify rice leaf diseases using image classification

PyTorch deep learning model for potato disease classification. Implements custom CNN and transfer learning (ResNet50, EfficientNet-B0) to identify Early Blight, Late Blight, and healthy potato leaves with 95%+ accuracy.

🌿 AI-powered web app for detecting plant diseases through leaf image analysis using deep learning (CNN).