Brainchip / Akida Image Classification
This is the finished Edge Impulse project for the tutorial 'Adding sight to your sensors'. From here you can acquire new training data, design impulses and train models.
About this project
Lamps and Plants and Bears, oh my!
Want to make the most of your device's camera and predict what is/is not present in your device's environment? Clone this project to build an embedded ML project to add intelligent sight to your device.
You can also follow our tutorial to guide you through building your image classification model, from data collection to deployment on embedded devices.
Sensor & Block Information
- Image data
- Image DSP block for normalizing image files
- Transfer Learning block with prediction outputs: "lamp", "plant", "unknown"
Download block output
| Title | Type | Size | |
|---|---|---|---|
| Image training data | NPY file | 221 windows | |
| Image training labels | NPY file | 221 windows | |
| Image testing data | NPY file | 58 windows | |
| Image testing labels | NPY file | 58 windows | |
| Transfer learning with Akida model | TensorFlow Lite (float32) | 3 MB | |
| Transfer learning with Akida model | TensorFlow Lite (int8 quantized) | 1 MB | |
| Transfer learning with Akida model | MetaTF | 1024 KB | |
| Transfer learning with Akida model | TensorFlow SavedModel | 3 MB | |
| Transfer learning with Akida model | Keras h5 model | 3 MB |
Clone project
You are viewing a public Edge Impulse project. Clone this project to add data or make changes.
Run this model
Scan QR code or launch in browser
Summary
Data collected
289 itemsProject info
| Project ID | 115634 |
| Project version | 7 |
| License | Apache 2.0 |
