[Code Addition Request]: Explainable AI: Scene Classification and Grad-CAM Visualization

[inkerton]

Have you completed your first issue?

• I have completed my first issue

Guidelines

• I have read the guidelines
• I have the link to my latest merged PR

Latest Merged PR Link

#1109

Project Description

This project explores scene classification using deep learning models and enhances interpretability with Grad-CAM (Gradient-weighted Class Activation Mapping) visualizations. Leveraging TensorFlow and Keras, the model is trained on the Intel Image Classification dataset to recognize six scene categories: buildings, forest, glacier, mountain, sea, and street. Grad-CAM is employed to identify which regions of an image contribute most to the model’s classification decision, helping users understand and trust model predictions by visualizing which parts of each scene the model "sees."

Dataset:

• Name: Intel Image Classification Dataset
• Source: Kaggle
• Description: Contains natural scene images from around the world categorized into six classes, with a training set of 14,034 images and a test set of 3,000 images.

Full Name

inkerton

Participant Role

GSSOC

[github-actions]

🙌 Thank you for bringing this issue to our attention! We appreciate your input and will investigate it as soon as possible.

Feel free to join our community on Discord to discuss more!

[github-actions]

✅ This issue has been closed. Thank you for your contribution! If you have any further questions or issues, feel free to join our community on Discord to discuss more!