project · 2022 · Project
Smart Agricultural Image Processing
An Android app for on-device object detection in agriculture using a Single Shot Detector, with a TensorFlow model deployed on AWS as an API and a multi-label, multi-class classifier.
AndroidTensorFlowSSDAWS
A mobile-first computer-vision project: an Android application for object detection in an agricultural setting, built on a Single Shot Detector (SSD).
Model and deployment
The detection model was built with TensorFlow and deployed on AWS as an API service, with a multi-label, multi-class classifier for the kinds of overlapping categories real field imagery throws at you. A lot of the learning was in the evaluation: error analysis and choosing the right metrics for a multi-label problem, where plain accuracy quietly lies to you.