Guilherme Martins / Tomato_leaf_disease_detection Public

Target: Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz) 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.

Tomato_leaf_disease_detection

Este projeto utiliza os conceitos de TinyML para identificar doenças presentes em folhas de tomate a partir de fotografias, com intuito de auxiliar no monitoramento agrícola.

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 (5,991 items)

View all

caf5fa98-1dd1-44a8-8ce1-35fff6e06818___GCREC_Bact.Sp 5783

ID: 1078050162

Label: bacterial_spot

f1604e72-b6ee-4b8b-81fa-cf3acc501e17___GHLB2 Leaf 8752

ID: 1078071803

Label: late_blight

410dea1e-836e-4d41-9039-9cfc2ec30c1e___GH_HL Leaf 318.1

ID: 1078063868

Label: healthy

f93578b3-4b98-4b13-95c3-495c656963f4___RS_Erly.B 8340

ID: 1078058643

Label: early_blight

7c1dc810-54ee-4442-86d5-6994d4736d92___RS_Erly.B 6430

ID: 1078055794

Label: early_blight

a4547675-5ca9-48de-a334-deb20db0808c___GHLB_PS Leaf 34 Day 13

ID: 1078070212

Label: late_blight

b953a8c3-8f95-4c8d-9c82-7906eb23334f___JR_Sept.L.S 8469

ID: 1078085298

Label: septoria_leaf_spot

Tomato___Tomato_mosaic_virus_original_169a7634-85a7-4096-85a3-4e75de98defe___PSU_CG 2226.JPG_9febc2e2-eee8-4eba-96b6-b0c7dfce0586

ID: 1078080439

Label: mosaic_virus

Model accuracy (Unoptimized (float32))

Validation set

86.5%

Test set

80.7%

On-device performance (Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz), Quantized (int8))

Latency

1014 ms.

Peak RAM usage

70.9K

Flash usage

85.1K

Run this model

On any device

Clone project

Dataset summary

Data collected

5,991 items

Labels

bacterial_spot, early_blight, healthy, late_blight, mosaic_virus, septoria_leaf_spot

Project info

Project ID	439395
License	Apache 2.0
No. of views	45,031
No. of clones	1