Nordic Semiconductor / nrf_accel_hw 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.

nrf_accel_hw

A simple project using acceleration readouts coming from a hardware accelerometer. Used by machine_learning application in nRF Connect SDK.

About this project

This public Edge Impulse project does not have a README yet. Clone this project to add new data or retrain this project, or to deploy this project to a device.

Data (182 samples)

View all

tap.json.23n14m62

ID: 1594837796

Label: tap

Sample length: 1s

tap.json.23n4othv

ID: 1594837749

Label: tap

Sample length: 1s

tap.json.23n4pqu3

ID: 1594837748

Label: tap

Sample length: 1s

tap.json.23js1jo9

ID: 1594837839

Label: tap

Sample length: 1s

rotate.json.23n419v9

ID: 1594837788

Label: rotate

Sample length: 15s

tap.json.23n4qb10

ID: 1594837741

Label: tap

Sample length: 1s

updown.json.23hl0oq0

ID: 1594837845

Label: updown

Sample length: 30s

rotate.json.23n45f9s

ID: 1594837785

Label: rotate

Sample length: 20s

Model accuracy (Unoptimized (float32))

Validation set

98.2%

Test set

97.1%

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

Latency

5 ms.

Peak RAM usage

3.1K

Flash usage

16.6K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

22m 11s

Sensors

x, y, z @ 52Hz

Labels

idle, rotate, tap, updown

Project info

Project ID	33129
Project version	6
License	Apache 2.0
No. of views	25,919
No. of clones	38