Aiornot

🚀 Classification Model for Real and AI-Generated Images

This is a classification model designed to distinguish between real images and AI-generated images. It leverages the swin-tiny-patch4-window7-224 model, fine-tuned on the aiornot dataset.

🚀 Quick Start

The model is used to classify real images and AI generated images. It's based on the swin-tiny-patch4-window7-224 architecture, finetuned on the aiornot dataset.

💻 Usage Examples

Basic Usage

import torch
from transformers import AutoFeatureExtractor, AutoModelForImageClassification

labels = ["Real", "AI"]
feature_extractor = AutoFeatureExtractor.from_pretrained("Nahrawy/AIorNot")
model = AutoModelForImageClassification.from_pretrained("Nahrawy/AIorNot")

input = feature_extractor(image, return_tensors="pt")
with torch.no_grad():
  outputs = model(**input)
  logits = outputs.logits
prediction = logits.argmax(-1).item()
label = labels[prediction] 

📄 License

This project is licensed under the Apache-2.0 license.

📋 Model Information