Justin Lutz / Spresense-Potholes Public

Target: Sony Spresense (Cortex-M4F 156MHz) 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.

Spresense-Potholes

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 (733 items)

View all

263.projects-for-6320-km-roads-awarded-under-bharatmala

ID: 123984136

Label: no-pothole

341.Roadscheme-770x433

ID: 123984109

Label: no-pothole

45.roman-roads

ID: 123984301

Label: no-pothole

103.toll-roads-in-portugal

ID: 123984215

Label: no-pothole

126.Kyzylart%20Pass0

ID: 123984221

Label: no-pothole

118.pothole_Mumbai-770x433

ID: 123984674

Label: pothole

115.5141124_021519-ewn-5pm-natario-potholes-vid

ID: 123984670

Label: pothole

58.920x920

ID: 123984724

Label: pothole

Model accuracy (Unoptimized (float32))

Validation set

93.8%

Test set

81.3%

On-device performance (Sony Spresense (Cortex-M4F 156MHz), Quantized (int8))

Latency

1873 ms.

Peak RAM usage

130.7K

Flash usage

308.4K

Run this model

On any device

Clone project

Dataset summary

Data collected

733 items

Labels

no-pothole, pothole

Project info

Project ID	120486
Project version	1
License	No license attached
No. of views	15,857
No. of clones	19