This Python project includes a set of scripts designed to differentiate between real images and AI-generated images. It utilizes a fine-tuned ResNet152 model to classify images into these two categories effectively.
- Data Setup: Scripts to prepare and split images into training and testing sets, ensuring a variety of examples for both real and AI-generated images.
- Model Training: Adjustments and fine-tuning of the ResNet152 model for specific classification tasks.
- Image Prediction: Functions to predict whether new images are real or AI-generated, including visualization of these predictions.
- Accuracy Measurement: Utility functions to calculate and report the accuracy of the model during training and testing phases.