raven49963 / Dumbbell Standard Exercise Recognition Public

Target: Arduino UNO Q (Qualcomm QRB2210) 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.

Dumbbell Standard Exercise Recognition

Images

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 (2,414 items)

View all

idle_01.s121

ID: 2402339866

Label: idle

perfect_02.s337

ID: 2402340535

Label: perfect

back_arch_03.s811

ID: 2402337238

Label: back_arch

idle_01.s1045

ID: 2402340020

Label: idle

back_arch_04.s709

ID: 2402341181

Label: back_arch

back_arch_03.s799

ID: 2402337236

Label: back_arch

elbow_out_01.s391

ID: 2402338919

Label: elbow_out

elbow_out_02.s589

ID: 2402338375

Label: elbow_out

Model accuracy (Unoptimized (float32))

Validation set

100.0%

Test set

94.4%

On-device performance (Arduino UNO Q (Qualcomm QRB2210), Unoptimized (float32))

Latency

52 ms.

Flash usage

9.0M

Run this model

On any device

Clone project

Dataset summary

Data collected

2,414 items

Labels

back_arch, elbow_out, idle, perfect

Project info

Project ID	834421
License	3-Clause BSD
No. of views	10,072
No. of clones	1