EIDSP / IMU Exercise 20% Train Set without Augmentation 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.

IMU Exercise 20% Train Set without Augmentation

About this project

Time Series Data Augmentation Demo

Dataset: https://github.com/microsoft/Exercise-Recognition-from-Wearable-Sensors

Compare: https://studio.edgeimpulse.com/public/751681/latest

Data (137 samples)

View all

ccaa3668f419bc18

ID: 2267445221

Label: 13

Sample length: 26s

c6b687c5b9915646

ID: 2267445185

Label: 13

Sample length: 20s

d2c47f1d9f8602ba

ID: 2267445177

Label: 13

Sample length: 28s

44d2f710050660a0

ID: 2267445189

Label: 8

Sample length: 30s

80025130e0f789ea

ID: 2267445207

Label: 8

Sample length: 30s

6ec2e18b6772d551

ID: 2267445192

Label: 42

Sample length: 30s

32fb16fc53468150

ID: 2267445225

Label: 43

Sample length: 30s

2481679414bacfbb

ID: 2267445201

Label: 71

Sample length: 30s

Model accuracy (Unoptimized (float32))

Validation set

82.4%

Test set

66.4%

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

Latency

6 ms.

Peak RAM usage

4.1K

Flash usage

16.9K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

1h 6m 19s

Sensors

accel_x, accel_y, accel_z @ 50Hz

Labels

13, 23, 39, 41, 42 and 4 others

Project info

Project ID	757063
Project version	2
License	BSD 3-Clause Clear
No. of views	13,461
No. of clones	1