baotramduong/Explainable-AI-Scene-Classification-and-GradCam-Visualization

We will build and train a Deep Convolutional Neural Network (CNN) with Residual Blocks to detect the type of scenery in an image. In addition, we will also use a technique known as Gradient-Weighted Class Activation Mapping (Grad-CAM) to visualize the regions of the inputs and help us explain how our CNN models think and make decision.

25
/ 100
Experimental

This project helps you automatically categorize images by the type of scene they depict, such as a forest, beach, or city. It takes an image as input and outputs the predicted scene category. Additionally, it visualizes the specific areas of the image that led to that classification, helping you understand why the AI made its decision. This is useful for anyone working with large collections of images who needs to organize them or verify an automated classification.

No commits in the last 6 months.

Use this if you need to classify images by scene type and want to understand which parts of the image are most influential in the classification.

Not ideal if you need to classify images based on object recognition or person identification rather than general scene types.

image-classification visual-content-analysis scene-understanding machine-vision explainable-ai
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

7

Forks

2

Language

Jupyter Notebook

License

Last pushed

Sep 10, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/baotramduong/Explainable-AI-Scene-Classification-and-GradCam-Visualization"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.