Arnulfo Silva / TI-ML-Terrain-Recognition Public

Target: TI LAUNCHXL-CC1352P (Cortex-M4F 48MHz) 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.

TI-ML-Terrain-Recognition

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 (186 samples)

View all

Wood.json.2vandpgr.ingestion-6d949d94fb-npt5b.json.2vbkn7no

ID: 99028411

Label: Wood

Sample length: 5s

Carpet.json.2v68j1qk.ingestion-7558d88f45-lsf97.json.2vbkn5uq

ID: 99028481

Label: Carpet

Sample length: 3s

Wood.json.2vanm4mq.ingestion-6d949d94fb-4l4wk.json.2vbkn86m

ID: 99028402

Label: Wood

Sample length: 5s

Brick.json.2varjvko.ingestion-6d949d94fb-4l4wk.json.2vbkn5cf

ID: 99028519

Label: Brick

Sample length: 10s

Carpet.json.2v68938v.ingestion-7558d88f45-k9jh8.json.2vbkn6gm

ID: 99028469

Label: Carpet

Sample length: 3s

Brick.json.2varmqgn.ingestion-6d949d94fb-f7wg7.json.2vbkn58a

ID: 99028527

Label: Brick

Sample length: 10s

Foam.json.2v6datj1.ingestion-7558d88f45-k9jh8.json.2vbkn6ha

ID: 99028466

Label: Foam

Sample length: 5s

Wood.json.2vanta4m.ingestion-6d949d94fb-f7wg7.json.2vbkn87o

ID: 99028388

Label: Wood

Sample length: 5s

Model accuracy (Unoptimized (float32))

Validation set

96.5%

Test set

88.9%

On-device performance (TI LAUNCHXL-CC1352P (Cortex-M4F 48MHz), Unoptimized (float32))

Latency

9 ms.

Peak RAM usage

3.6K

Flash usage

23.4K

Run this model

On any device

Clone project

Dataset summary

Data collected

15m 0s

Sensors

x, y, z @ 50Hz

Labels

Brick, Carpet, Foam, Turf, Wood

Project info

Project ID	50843
Project version	9
License	No license attached
No. of views	5,482
No. of clones	0