I developed a deep learning model for plant disease detection and classification using a hybrid CNN architecture (VGG16 + ResNet50). The model achieved 98.89% training, 99.53% validation, and 97.45% testing accuracy across multiple plant disease categories. To enhance accuracy and generalization, I applied data augmentation, transfer learning, and optimization techniques such as batch normalization, dropout, and exponential learning rate decay. Additionally, I implemented early stopping, model checkpointing, and adaptive learning rate schedules to prevent overfitting and ensure stable training. This project highlights my expertise in computer vision, deep learning, and real-world agricultural applications.