Edge Impulse Experts / Gesture detection Public

Target: Nordic nRF52840 DK (Cortex-M4F 64MHz) 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.

Gesture detection

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 (293 samples)

View all

left-right.6bpltme0.s44

ID: 2467141524

Label: left-right

Sample length: 1s

idle.6bpm8e7b

ID: 2467141425

Label: idle

Sample length: 1m 0s

circle.6bplo55l.s37

ID: 2467141623

Label: circle

Sample length: 1s

circle.6bplo55l.s46

ID: 2467141630

Label: circle

Sample length: 1s

left-right.6bpltme0.s27

ID: 2467141511

Label: left-right

Sample length: 1s

idle.6bpmeorp.s34

ID: 2467141582

Label: idle

Sample length: 1s

left-right.6bpltme0.s7

ID: 2467141495

Label: left-right

Sample length: 1s

idle.6bpmeorp.s39

ID: 2467141586

Label: idle

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

96.6%

Test set

96.7%

On-device performance (Nordic nRF52840 DK (Cortex-M4F 64MHz), Quantized (int8))

Latency

9 ms.

Peak RAM usage

1.4K

Flash usage

15.3K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

5m 52s

Sensors

Ax, Ay, Az @ 52Hz

Labels

circle, idle, left-right, random-motion

Project info

Project ID	848088
Project version	1
License	3-Clause BSD
No. of views	6,099
No. of clones	1