Image Classification
Keras
CNN / README.md
litav's picture
Update README.md
1a44747 verified
|
raw
history blame
754 Bytes
metadata
license: apache-2.0

Real vs AI-Generated Image Classification

This project provides a Convolutional Neural Network (CNN) model for classifying images as either 'real' or 'fake'. CNN is a type of deep learning model specifically designed to process and analyze visual data by applying convolutional layers that automatically detect patterns and features in images. Our CNN model is based on 2,800 real images and AI-generated images, which are divided equally.

Our goal is to accurately classify the source of the image with at least 85% accuracy and achieve at least 80% in the Recall test.

  1. Installation Instructions
  2. Usage Instructions
  3. Model Architecture
  4. Training Details
  5. Evaluation
  6. Examples
  7. Contributing
  8. License