Edge Impulse Experts / Bangle Activities 2 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.

Bangle Activities 2

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 (531 samples)

View all

activity_2024_10_26_18_07.s4

ID: 1318596853

Label: running

Sample length: 3,040ms

acti_2024_10_27_18_40.s4

ID: 1318596875

Label: running

Sample length: 3,040ms

acti_2024_10_31_18_58_3.s12

ID: 1321182810

Label: 3-rowing

Sample length: 3,040ms

acti_2024_10_31_19_02.s12

ID: 1321152695

Label: 4-push up

Sample length: 3,040ms

acti_2024_10_31_19_56.s32

ID: 1321284600

Label: sitting

Sample length: 3,040ms

acti_2024_10_27_19_16.s29

ID: 1318597361

Label: 5-pull up

Sample length: 3,040ms

acti_2024_10_27_18_40.s5

ID: 1318596901

Label: running

Sample length: 3,040ms

acti_2024_10_29_22_27.s25

ID: 1318670922

Label: 5-pull up

Sample length: 3,040ms

Model accuracy, Impulse #35 (Unoptimized (float32))

View 3 other experiments

Validation set

95.2%

Test set

89.9%

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

Latency

1 ms.

Peak RAM usage

1.6K

Flash usage

17.0K

Run this model

On any device

Clone project

Dataset summary

Data collected

26m 23s

Sensors

x, y, z @ 12.5Hz

Labels

3-rowing, 4-push up, 5-pull up, running, sitting, walking

Project info

Project ID	544247
License	Apache 2.0
No. of views	81,760
No. of clones	7