Extroverted-introvert/Crop-Disease-Detection-in-Uganda

AI for Agriculture: Classify cassava leaf diseases using PyTorch CNNs & ResNet50. Addresses food security in Uganda by enabling rapid, AI-driven diagnosis from images. Includes debugging, data prep, baseline, transfer learning, K-Fold CV, and submission. ## AI for Agriculture: Cassava Leaf Disease Classification This project addresses the challenge of identifying diseases in cassava plants, a staple crop in Uganda, using deep learning. By building and training a Convolutional Neural Network (CNN), this project aims to create a model capable of accurately classifying images of cassava leaves into five categories: one healthy class and four distinct disease classes (Green Mottle Virus, Bacterial Blight, Brown Streak Disease, and Mosaic Disease). The project is structured as a series of notebooks that guide the user from understanding common deep learning errors to building, training, and optimizing a sophisticated computer vision model for a real-world agricultural application. ### Project Overview As the second-largest provider of carbohydrates in Africa, cassava is a key food security crop grown by smallholder farmers because it can withstand harsh conditions. At least 80% of household farms in Sub-Saharan Africa grow this starchy root, but viral diseases are a major source of poor yields. With the help of data science, it may be possible to identify common diseases so they can be treated. Existing methods of disease detection require farmers to solicit the help of government-funded agricultural experts to visually inspect and diagnose the plants. This suffers from being labor-intensive, with a low supply of experts and high costs. As an added challenge, effective solutions for farmers must perform well under significant constraints, since African farmers may only have access to mobile-quality cameras and low-bandwidth internet. To combat this, this project leverages artificial intelligence to provide rapid and accurate diagnosis of crop diseases from images, helping farmers protect their yields. The project uses the Cassava Plant Disease Kaggle Dataset, which contains 21,367 labeled images collected during a regular survey in Uganda. Most images were crowdsourced from farmers taking photos of their gardens …