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

268.mumbai-potholes-twitter_650x400_41468331184

ID: 123984550

Label: pothole

24

ID: 123984754

Label: pothole

105.First_recycled_glass_and_plastic_road_in_NSW_at_Engadine

ID: 123984092

Label: no-pothole

341.Roadscheme-770x433

ID: 123984109

Label: no-pothole

38.pothole

ID: 123984634

Label: pothole

135.roads

ID: 123984216

Label: no-pothole

32.500_F_286554510_F1BCqu3yPcYlAvOvqI49RBEDLczwaFMf

ID: 123984339

Label: no-pothole

61.Roadways_Landscapes_023_cropped

ID: 123984278

Label: no-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	18,471
No. of clones	24