Major project
Agriculture & Food
Crop disease detection for low-bandwidth networks
Build a leaf disease model and deploy it as a light API that works on slow mobile networks, with monitoring.
The brief
Most farmers have slow mobile data. Build the leaf disease model, shrink it, and deploy it as a light API (or on the phone) that works on slow networks, with image compression, monitoring of predictions and a way to collect hard cases for retraining. Good looks like: a small model with measured accuracy, response times on a throttled network, and monitoring.
What you will build
- Train and evaluate the disease model
- Shrink it with quantisation or a smaller architecture
- Compress uploads and test on a throttled network
- Deploy the API in Docker with monitoring
- Collect low-confidence images for review
- Plan retraining with new field images
Free, open data to build it with
- PlantVillage dataset ↗ Kaggle
- PlantDoc field images ↗ GitHub
Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.