Running Deep Learning Based Plant Diseases Recognition

[adwnis123]

Hello,

How can I run:

https://github.com/spMohanty/PlantVillage-Dataset#start-of-content

or smoething similar,

or this:

https://github.com/saroz014/Plant-Diseases-Recognition

on Raspberry Pi ? Or something that does plant disease image processing with CNN?

Thank you...

 

[andre_luis]

How can I run:

How about trying to do what is stated on the README.md link and see what comes next?

 

[adwnis123]

Ok, I did:

git clone https://github.com/spMohanty/PlantVillage-Dataset
cd PlantVillage-Dataset

then what?

To start running commands randomly by luck?

 

[andre_luis]

Did you try to run the python command ? Did you see that there is an issue on which others requested to improve the Readme file ? If by experiments and by looking the source .py code you are not able to identify what to do, I would recommend you add your request at the Issue tab on the Git page, as 2 others have done.

 

[eziggurat]

Have you tried installing tensorflow for PI? https://maker.pro/raspberry-pi/tuto...-learning-software-tensorflow-on-raspberry-pi

If the speed is inadequate using a PI, you could always plug in a movidius or coral to the PI.

 

[Tieny]

Have you tried installing tensorflow for PI? https://maker.pro/raspberry-pi/tuto...-learning-software-tensorflow-on-raspberry-pi

If the speed is inadequate using a PI, you could always plug in a movidius or coral to the PI.

That's right, it just a dataset , you need a framework for Machine Learning like lite tensorflow on the Pi but the learning time will slowd due to CPU core and dont have GPU support.

Tiep Ngo

 

[eziggurat]

You won't be learning on a pi but inference. You train on a PC with gpu and deploy the model to the pi. Coral or gpu on the pi maybe enough to perform inference and it is all depend on your model size and precision.

 

[Tieny]

You won't be learning on a pi but inference. You train on a PC with gpu and deploy the model to the pi. Coral or gpu on the pi maybe enough to perform inference and it is all depend on your model size and precision.

Thanks, never try that but it's a good idea

Tiep Ngo