Terrain Classification

[MohanRocks999]

Pull Request for DL-Simplified 💡

Issue Title : Terrain Recognition

• Info about the related issue (Aim of the project) :
• Name: Mohana Krishna
• GitHub ID: https://github.com/MohanRocks999
• Email ID: [email protected]
• Idenitfy yourself: (Mention in which program you are contributing in. Eg. For a JWOC 2022 participant it's, JWOC Participant) I am Contributing in GSSoC 2024

Closes: #636

Add-ons or changes made 📃

Trained a Image Classification using various deep learning algorithms. This include DeepViT (Not just Vision Transformer), EfficientNet B3, DeiT3 (Data efficient image transformer) and YoloV8 that classifies images on 5 different types of terrains - coast, mountain, glacier, forest and desert.

Type of change ☑️

• [ X] New feature - A Terrain Classification using the respective neural network architecture using pytorch.

How Has This Been Tested? ⚙️

The Model have been evaluated extensively with a validation dataset comprising of 2000 images (400 images per class) and a test dataset of 500 images.

Checklist: ☑️

• [ X] My code follows the guidelines of this project.
• [ X] I have performed a self-review of my own code.
• [X ] I have commented my code, particularly wherever it was hard to understand.
• I have made corresponding changes to the documentation.
• [ X] My changes generate no new warnings.
• [X ] I have added things that prove my fix is effective or that my feature works.
• [ ]X Any dependent changes have been merged and published in downstream modules.

[github-actions]

Our team will soon review your PR. Thanks @MohanRocks999 :)

[abhisheks008]

What's the issue number?

[MohanRocks999]

The issue number is 636

[abhisheks008]

Hi @MohanRocks999 remove the extra files and follow the project structure for this project.

[MohanRocks999]

What files needs to be removed and do you want me to add all the models in one single notebook?

[abhisheks008]

It'll be better to have a single notebook file (.ipynb) where all the models and EDAs can be implemented together.

[MohanRocks999]

The changes has been as per your request. check it out.

[abhisheks008]

Hi @MohanRocks999 everything looks good to me. Some minor changes are required,

1. Follow the README template and update the README as per the given points. Here is the template: https://github.com/abhisheks008/DL-Simplified/blob/main/.github/readme_template.md
2. Insert the resulted images inside the Images folder including the confusion matrix, data visualization and so on.
3. Remove the .gitignore file.

[MohanRocks999]

The requested changes has been done. Please check the changes as soon as you can.

[abhisheks008]

Looks good to me. Approved ✅
@MohanRocks999