Edge Impulse Inc. / Person vs unknown Public

Target: Cortex-M4F 80MHz Clone this project

Welcome to Edge Impulse, the largest community of edge AI developers!
This is a public Edge Impulse project, use the navigation bar to see all data and models in this project; or clone to retrain or deploy to any edge device.

Person vs unknown

Images

About this project

Person vs unknown

Person detection classifier trained

on a subset of the MS COCO 2017 for the person label and
on a mix of images collected by Edge Impulse team, a houses images dataset from Ahmed, Eman and Moustafa, Mohamed

Data (802 items)

View all

resized_10275

ID: 289659695

Label: person

137_bedroom

ID: 289659452

Label: unknown

129_kitchen

ID: 289659491

Label: unknown

resized_10232

ID: 289659732

Label: person

116_kitchen

ID: 289659546

Label: unknown

resized_10116

ID: 289659829

Label: person

resized_10102

ID: 289659842

Label: person

resized_10255

ID: 289659714

Label: person

Model accuracy (Unoptimized (float32))

Validation set

98.4%

Test set

98.7%

On-device performance (Cortex-M4F 80MHz, Quantized (int8))

Latency

795 ms.

Peak RAM usage

280.0K

Flash usage

206.6K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

802 items

Labels

person, unknown

Project info

Project ID	233515
Project version	2
License	BSD 3-Clause Clear
No. of views	101,911
No. of clones	48