EIDSP / IMU Exercise 20% Train Set with 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 with Augmentation

About this project

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

Data (193 samples)

View all

b8e7715afc8f469c

ID: 2267396509

Label: 13

Sample length: 30s

5bc2bc9a499bb207

ID: 2267396507

Label: 23

Sample length: 30s

626cae50b68235c3.simulated_0.61d7ng4p

ID: 2267396557

Label: 50

Sample length: 29s

bf07e93fa69ff2e7

ID: 2267396490

Label: 8

Sample length: 30s

b9142a39ffe248ac.simulated_0.61d7ksqo

ID: 2267396526

Label: 42

Sample length: 30s

f6d2825b76397d5b

ID: 2267396494

Label: 8

Sample length: 30s

1bf0092790ea4c11.simulated_1.61d7nave

ID: 2267396555

Label: 39

Sample length: 19s

97ea9796f7c08703

ID: 2267396498

Label: 13

Sample length: 21s

Model accuracy (Unoptimized (float32))

Validation set

85.4%

Test set

74.1%

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 33m 33s

Sensors

accel_x, accel_y, accel_z @ 50Hz

Labels

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

Project info

Project ID	751681
Project version	3
License	BSD 3-Clause Clear
No. of views	5,753
No. of clones	3