Louis Moreau / Face detection - FOMO - bigger dataset Public

Face detection - FOMO - bigger dataset

Object detection

About this project

Face detection using FOMO

FOMO-Faces.png

Want to see a deeper explanation about FOMO and a live demo? See Arm AI Tech Talk about FOMO

Dataset Information

This project is using a subset of the FFHQ dataset where the bounding boxes have been labeled manually by Edge Impulse team.

Sensor & Block Information

  • Camera module with input images 96 x 96 pixels
  • Image block to normalize the image data, and keep the color depth to RGB
  • FOMO transfer learning block based on MobileNetV2 0.35

Interested in adding object detection capabilities to your constrained edge devices? Clone this project to build an object detection project to detect cans and bottles on the tiniest of devices!

Read more on our announcement blog to find out more about FOMO and to learn how to build your object detection project, from data collection to deployment on embedded devices.

37071.2u8b4v2h
face.3334r17s.ingestion-6547c9496d-htc55
37044.2u8b4cne
37887.2u5qmhor
37584.2u8d115i
37056.2u8b49af
37060.2u8b4le9
37888.2u5qmjae

Run this model

On any device

Dataset summary

Data collected
517 items
Labels
face

Project info

Project ID 116394
Project version 2
License BSD 3-Clause Clear
No. of views 15,083
No. of clones 94