Nathaniel Felleke / Trash Image Detection
This is your Edge Impulse project. From here you acquire new training data, design impulses and train models.
About this project
Mapping Litter in Cities
Introduction
A prototype of a roadside litter detection device that maps trash in cities and helps locate pickup locations. Using an image recognition model made in Edge Impulse Studio, the device is able to classify whether images of the road contain trash or not. If there is trash, a Blues Wireless Notecard retrieves the GPS location and transmits the classification to the cloud.
Hackster.io Project
Creating your first impulse (100% complete)
Acquire data
Every Machine Learning project starts with data. You can capture data from a development board or your phone, or import data you already collected.
Design an impulse
Teach the model to interpret previously unseen data, based on historical data. Use this to categorize new data, or to find anomalies in sensor readings.
Deploy
Package the complete impulse up, from signal processing code to trained model, and deploy it on your device. This ensures that the impulse runs with low latency and without requiring a network connection.
Download block output
| Title | Type | Size | |
|---|---|---|---|
| Image training data | NPY file | 764 windows | |
| Image training labels | NPY file | 764 windows | |
| Image testing data | NPY file | 208 windows | |
| Image testing labels | NPY file | 208 windows | |
| Transfer learning model | TensorFlow Lite (float32) | 2 MB | |
| Transfer learning model | TensorFlow Lite (int8 quantized) | 625 KB | |
| Transfer learning model | TensorFlow SavedModel | 2 MB | |
| Transfer learning model | Keras h5 model | 2 MB |
Clone project
Summary
Data collected
972 itemsProject info
| Project ID | 110140 |
| Project version | 4 |
| License | No license attached |
|
|
