abhisheks008 / ML-Crate

ML-Crate stands as the ultimate hub for a multitude of exciting ML projects, serving as the go-to resource haven for passionate and dedicated ML enthusiasts!🌟💫 Devfolio URL, https://devfolio.co/projects/mlcrate-98f9
https://quine.sh/repo/abhisheks008-ML-Crate-409463050
MIT License
192 stars 216 forks source link

Mineral classification #668

Closed tanuj437 closed 3 months ago

tanuj437 commented 3 months ago

Pull Request for ML-Crate 💡

Issue Title: Mineral Classification

Closes: #467 number that will be closed through this PR

Describe the add-ons or changes you've made 📃

I've included a full README.md file in the mineral classification project's folder. This README.md file contains thorough descriptions and visual representations of numerous analyses and model outputs for the mineral classification problem. It contains explanations and graphics for label distribution methods such as count distribution, and model performance outputs (SVM, Random Forest, K-NN, CNN, Logistic Regression, Decision Tree Classification, Extra Tree Classification). These additions are intended to improve the clarity and understanding of the project's visual and analytical components.

Type of change ☑️

What sort of change have you made:

How Has This Been Tested? ⚙️

I have tested it on webapp with the same images of mineral which we have trained the model. Since i tested which all types of minerals photos and it accurately predict the mineral for each input image

Checklist: ☑️

github-actions[bot] commented 3 months ago

Our team will soon review your PR. Thanks @tanuj437 :)

tanuj437 commented 3 months ago

@abhisheks008 Reduced the number of images in image folder as well as put the each mineral photo in it too. Can't reduce more images in there

tanuj437 commented 3 months ago

@abhisheks008 yes those are the datapoints which trained the model...img folder in Dataset is actually the dataset folder

So do i put just one image for each mineral of that folder as well?

abhisheks008 commented 3 months ago

@abhisheks008 yes those are the datapoints which trained the model...img folder in Dataset is actually the dataset folder

So do i put just one image for each mineral of that folder as well?

If you are sharing the dataset URL in the Dataset/README file then no need to add the datapoints (images). This will reduce the space occupancy of the project folder.

tanuj437 commented 3 months ago

@abhisheks008 All changes Done

abhisheks008 commented 3 months ago

Upload a demonstration video of the working of the web app and attach the same in the Web App/README, so that others can have an idea about the working of the web app.

tanuj437 commented 3 months ago

@abhisheks008 Done added