Beta / trash image classification Public

Target: Espressif ESP-EYE (ESP32 240MHz) 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.

trash image classification

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 (6,581 items)

View all

metal_02669

ID: 2462339155

Label: metal

metal_00334

ID: 2462336225

Label: metal

glass_02242

ID: 2462333398

Label: glass

paper_00549

ID: 2462339734

Label: paper

metal_01876

ID: 2462337658

Label: metal

glass_01478

ID: 2462332875

Label: glass

paper_02892

ID: 2462342055

Label: paper

plastic_02110

ID: 2462344772

Label: plastic

Model accuracy, Impulse #12 (Unoptimized (float32))

View 9 other experiments

Validation set

86.0%

Test set

85.0%

On-device performance (Espressif ESP-EYE (ESP32 240MHz), Quantized (int8))

Latency

4688 ms.

Peak RAM usage

416.1K

Flash usage

650.6K

Run this model

On any device

Clone project

Dataset summary

Data collected

6,581 items

Labels

glass, metal, paper, plastic

Project info

Project ID	847334
License	3-Clause BSD
No. of views	29,781
No. of clones	4