Detect common tomato leaf diseases using a deep learning model built with PyTorch + MobileNetV2, deployed with Streamlit.

This tool helps farmers, students, and researchers identify tomato plant health conditions from leaf images.

The complete source code is available in this repository, and the dataset can be found here.

1. Upload a photo of a tomato leaf (JPG/PNG format) or capture one using your camera.
2. Wait a few seconds while the model analyzes the image.
3. The app will display:
   • The predicted disease (or “Healthy”),
   • Confidence level, and
   • Prevention tips.

• Architecture: MobileNetV2 (Transfer Learning)
• Framework: PyTorch
• Input Size: 224 × 224 pixels
• Output Classes:
  • Bacterial Spot
  • Early Blight
  • Late Blight
  • Leaf Mold
  • Septoria Leaf Spot
  • Spider Mites
  • Target Spot
  • Tomato Yellow Leaf Curl Virus
  • Tomato Mosaic Virus
  • Powdery Mildew
  • Healthy

The model was trained on tomato leaf datasets collected from open agricultural image repositories.

This application is for educational and research purposes only.
It should not be used as a substitute for professional agricultural advice.
Always consult an expert before applying treatments to crops.

You can test the app with your own tomato leaf photo, or use sample images from the examples folder.

Developed by Eka Dwipayana
🔗 Tomato Disease Detector on Streamlit Cloud
🔗 LinkedIn