Louis Moreau / Face detection - FOMO - Embedded Online Conference Public

Target: Arduino Portenta H7 (Cortex-M7 480MHz) 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.

Face detection - FOMO - Embedded Online Conference

Object detection

About this project

Face detection using FOMO

This project is using a subset of the FFHQ dataset.

The model has been trained on 96x96 greyscale images

Data (406 items)

View all

37975.2u5qni7e

ID: 95783753

37602.2u8d12em

ID: 95783582

37995.2u5qnp04

ID: 95783740

37946.2u5qnejn

ID: 95783761

37064.2u8b4b1h

ID: 95783671

37893.2u5qmvfj

ID: 95783811

37902.2u5qmtbi

ID: 95783813

37888.2u5qmjae

ID: 95783837

Model accuracy, Image data, Image, Object Detection (Images) #3 (Clone of version #2) (Unoptimized (float32))

View 2 other experiments

Validation set

77.6%

Test set

53.4%

On-device performance (Arduino Portenta H7 (Cortex-M7 480MHz), Quantized (int8))

Latency

45 ms.

Peak RAM usage

240.0K

Flash usage

63.6K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

406 items

Labels

face

Project info

Project ID	96468
Project version	1
License	BSD 3-Clause Clear
No. of views	89,261
No. of clones	364