Added Grad-CAM Heatmap Visualizer

[ParasSethi737]

Pull Request for DL-Simplified 💡

Issue Title : Grad-CAM Heatmap Visualization for CNN Model Interpretability

• Info about the related issue (Aim of the project) : This project aims to implement Grad-CAM for visualizing class-specific heatmaps in CNN-based image classification models, such as ResNet50, VGG19, and Xception. The goal is to better understand the decision-making process of the model by visualizing which parts of the input image influenced the predictions the most.

• Name: Paras Sethi

• GitHub ID: ParasSethi737

• Email ID: paras.sethi340@gmail.com

• Identify yourself: SWOC Participant

Closes: #880

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

• Implemented Grad-CAM heatmap visualization for popular CNN models (ResNet50, VGG19, and Xception).
• Added functionality to overlay heatmaps on input images and visualize them.
• Incorporated the ability to save and display the output heatmap images.
• Structured the project with a clear folder structure, including necessary Python files and images.

Type of change ☑️

What sort of change have you made:

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Code style update (formatting, local variables)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested? ⚙️

• Tested the heatmap generation for various CNN models (ResNet50, VGG19, Xception) on sample images.
• Verified that the generated heatmaps align with model predictions, highlighting areas that influence the classification.

Checklist: ☑️

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

[github-actions]

Our team will soon review your PR. Thanks @ParasSethi737 :)

[abhisheks008]

Hi @ParasSethi737 looks good to me. Can you please test the models using more images, instead of using one image only? At least 4 images will do it for me.

[ParasSethi737]

Hi @abhisheks008, I have updated the code to test the models with 4 images as requested.

[abhisheks008]

Your PR is approved and ready to be merged!!
@ParasSethi737