Louis (Demo) / Fitness classifier 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.

Fitness classifier

Accelerometer

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 (40 samples)

View all

no-movement.json.2879ab3e

ID: 138897373

Label: no-movement

Sample length: 10s

rest.json.287a5tod

ID: 138897352

Label: rest

Sample length: 30s

squats.json.2879s1hm

ID: 138897360

Label: squats

Sample length: 30s

no-movement.json.2879baqo

ID: 138897371

Label: no-movement

Sample length: 10s

no-movement.json.2879c6kj

ID: 138897370

Label: no-movement

Sample length: 10s

jumping-jacks.json.289kdkgm

ID: 138897348

Label: jumping-jacks

Sample length: 20s

no-movement.json.28799af0

ID: 138897375

Label: no-movement

Sample length: 10s

rest.json.287a4jmf

ID: 138897353

Label: rest

Sample length: 30s

Model accuracy, Time series data, Spectral Analysis, Neural Network (Keras) #1 (16 - 8 - 0.25dropout - 8) (Unoptimized (float32))

View 1 other experiment

Validation set

100.0%

Test set

99.5%

On-device performance (Cortex-M4F 80MHz, Unoptimized (float32))

Latency

8 ms.

Peak RAM usage

4.7K

Flash usage

45.9K

Run this model

On any device

Clone project

Dataset summary

Data collected

17m 45s

Sensors

accX, accY, accZ @ 62.5Hz

Labels

jumping-jacks, no-movement, rest, squats

Project info

Project ID	36037
Project version	3
License	BSD 3-Clause Clear
No. of views	21,376
No. of clones	48