Louis (Demo) / Person Detection Public

Louis (Demo) / Person Detection

This is your Edge Impulse project. From here you acquire new training data, design impulses and train models.

Object detection

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.

Screen-Shot-2022-04-21-at-18.03.55.png

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 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 items

Project info

Project ID 96757
Project version 11
License No license attached