Gerrit / plant-disease 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.

plant-disease

Images

About this project

This project uses the New Plant Diseases Dataset to train and validate a classifier that can detect 9 different plant diseases on tomato plants. The total dataset is divided into a 80/20 ratio of training and validation data.

Data (22,917 items)

View all

5ba3b6f4-7b05-4588-8063-078c48268e88___Keller.St_CG 1935

ID: 121524233

Label: tomato-leaf-spot

3d1ab8b2-d61c-4ab1-9222-52bf63eb0315___RS_HL 0548_flipTB

ID: 121514657

Label: tomato-healthy

0d922399-7ba5-4d12-b84e-bb4b966c58ae___GCREC_Bact.Sp 6307

ID: 121515809

Label: tomato-bacterial-spot

4c2c45b2-7e33-4b1d-9125-b14b5ccafedd___RS_HL 9991_newPixel25

ID: 121515142

Label: tomato-healthy

ca7035fa-f55d-49c7-9d89-3d513c8e35b1___RS_Erly.B 7556_180deg

ID: 121519202

Label: tomato-early-blight

4b98528b-25af-4f6d-b094-9b69eac52082___Com.G_TgS_FL 0932

ID: 121509019

Label: tomato-target-spot

f3113f81-fff3-4b7d-b171-7315216c4d10___Crnl_L.Mold 8683_flipTB

ID: 121523221

Label: tomato-leaf-mold

e330dc16-fdf9-4eee-8b09-88bfb5537180___RS_Erly.B 7601_180deg

ID: 121518714

Label: tomato-early-blight

Model accuracy (Unoptimized (float32))

Validation set

92.4%

Test set

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

Latency

1021 ms.

Peak RAM usage

260.1K

Flash usage

325.0K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

22,917 items

Labels

testing, tomato-bacterial-spot, tomato-early-blight, tomato-healthy, tomato-late-blight and 6 others

Project info

Project ID	117043
Project version	1
License	No license attached
No. of views	123,529
No. of clones	51