Heatmap Visualization of a Image Classification Model like Xception using GRAD-CAM

[AMS003010]

Deep Learning Simplified Repository (Prop.osing new issue)

:red_circle: Project Title : Heatmap Visualization of a Image Classification Model like Xception using GRAD-CAM :red_circle: Aim : GRAD-CAM, which stands for Gradient-weighted Class Activation Mapping, is a technique used in the field of computer vision to visualize the regions of an image that are important for a convolutional neural network's decision-making process.So I would like to use Deep learning techniques like GRAD-CAM to explain why the Xception model is classifying that as an "Persian cat" ( Or anything else ) visually through a heatmap. :red_circle: Dataset : Not applicable as I will be using an Xception model with the imagenet weights to explain the reson it classified that as that using GRAD CAM :red_circle: Approach : Since ML techniques like CNN are essentially "Black Boxes", it is hard for us to understand why it made that choice. Using GRAD-CAM we are able to explain why the CNN model made that particular choice that it did. It helps us to visually understand the "why" of the classification.

---

📍 Follow the Guidelines to Contribute in the Project :

• You need to create a separate folder named as the Project Title.
• Inside that folder, there will be four main components.
  • Images - To store the required images.
  • Dataset - To store the dataset or, information/source about the dataset.
  • Model - To store the machine learning model you've created using the dataset.
  • requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
• Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

---

:red_circle::yellow_circle: Points to Note :

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

:white_check_mark: To be Mentioned while taking the issue :

• Full name : Abhijith M S
• GitHub Profile Link : https://github.com/AMS003010
• Email ID : [email protected]
• Participant ID (if applicable):
• Approach for this Project : Implementation, Code and Results will be provided
• What is your participant role: GSSOC'24

---

Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[github-actions[bot]]

Thank you for creating this issue! We'll look into it as soon as possible. Your contributions are highly appreciated! 😊

[abhisheks008]

Nice approach. Issue assigned to you @AMS003010. Make sure you complete this issue within the deadline of August 10th, 2024.

[AMS003010]

@abhisheks008
I made the PR Please do review

[ParasSethi737]

🔴 Request for Assignment:
Hello @abhisheks008,

I would like to request assignment for the issue titled "Heatmap Visualization of an Image Classification Model like Xception using GRAD-CAM". For this project, I plan to use the following models(using pre-trained weights):

• Xception
• VGG19
• ResNet50

I will be implementing the Grad-CAM technique to visualize the regions in images that are important for the model's decision-making process. The goal is to generate heatmaps that help explain why the model classifies an image in a certain way.

🔴 Participant Details:

• Full Name: Paras Sethi
• GitHub Profile: https://github.com/ParasSethi737
• Email ID: [email protected]
• Approach: I will focus on the implementation of Grad-CAM for each of the models mentioned above. I will provide the code and results as part of the project, along with visualizations and conclusions.
• What is your participant role: SWOC

Looking forward to contributing to this project!

[abhisheks008]

Hi @ParasSethi737 go ahead. Issue assigned to you!

[ParasSethi737]

@abhisheks008 I have made the PR, please do review.

[github-actions[bot]]

Hello @ParasSethi737! Your issue #880 has been closed. Thank you for your contribution!