Louis (Demo) / Person Detection
This is your Edge Impulse project. From here you acquire new training data, design impulses and train models.
Maintenance window planned next Monday, 04/29 at 5:00AM UTC (more)
About this project
Person Detection using Object Detection Transfer learning
Person detection project trained on a subset of the MS COCO 2017.
Key info
- Sensor type: Camera
- DSP block type: Image processing, RGB, resize 320x320, squash
- Learning block type: MobileNetV2 SSD FPN-Lite
Overview
For this project, we are using the Object Detection training block which fine tunes a pre-trained object detection model on your data. It gives a good performance even with relatively small image datasets. This object detection learning block relies on MobileNetV2 SSD FPN-Lite 320x320.
Download block output
| Title | Type | Size | |
|---|---|---|---|
| Image training data | NPY file | 147 windows | |
| Image training labels | JSON file | 147 windows | |
| Image testing data | NPY file | 35 windows | |
| Image testing labels | JSON file | 35 windows | |
| Object detection model (version #1) | TensorFlow Lite (float32) | 11 MB | |
| Object detection model (version #1) | TensorFlow Lite (int8 quantized) | 4 MB | |
| Object detection model (version #1) | TensorFlow SavedModel | 10 MB | |
| Object detection model (version #2) | TensorFlow Lite (float32) | 11 MB | |
| Object detection model (version #2) | TensorFlow Lite (int8 quantized) | 4 MB | |
| Object detection model (version #2) | TensorFlow SavedModel | 10 MB |
Clone project
You are viewing a public Edge Impulse project. Clone this project to add data or make changes.
Summary
Data collected
182 itemsProject info
| Project ID | 40479 |
| Project version | 11 |
| License | No license attached |
