real-vs-fake-image-classifier

Real vs Fake Image Classifier (ViT)

This model classifies images as real or fake using a Vision Transformer (ViT).

Model Info

• Architecture: ViT Base Patch16 224
• Training Accuracy: 90.75%
• Validation Accuracy: 93.38%
• Dataset: Your dataset description

Usage

import torch
from PIL import Image
import torchvision.transforms as transforms

# Load full model
model = torch.load("model.pth")
model.eval()

# Transform input image
transform = transforms.Compose([
    transforms.Resize((224,224)),
    transforms.ToTensor()
])

image = Image.open("test.jpg")
image = transform(image).unsqueeze(0)
pred = torch.argmax(model(image))
print("Prediction:", "Real" if pred.item()==1 else "Fake")