TIGAS/
├── LICENSE                     # MIT License
├── README.md                   # This file
├── train/
│   ├── annotations01.csv       # Training annotations (128,776 entries)
│   └── images/
│       ├── ADM/
│       │   ├── 0_real/         # Real images from ImageNet
│       │   └── 1_fake/         # Generated by ADM
│       ├── art001/
│       │   ├── 0_real/
│       │   └── 1_fake/
│       ├── art002_1/ ... art002_4/
│       ├── biggan/
│       ├── DALLE2/
│       ├── face/
│       ├── gaugan/
│       ├── Glide/
│       ├── Midjourney/
│       ├── sd_xl/
│       ├── sd14/
│       ├── sd15_1/
│       ├── sd15_2/
│       ├── stargan/
│       ├── VQDM/
│       └── wuk/
└── test/
    └── annotations01.csv       # Test annotations (14,126 entries)

image_path,label
images\ADM\0_real\ILSVRC2012_val_00000005.JPEG,0
images\Midjourney\1_fake\image_001.png,1

import pandas as pd
from pathlib import Path
from PIL import Image

# Load annotations
data_root = Path("TIGAS")
train_df = pd.read_csv(data_root / "train" / "annotations01.csv")
test_df = pd.read_csv(data_root / "test" / "annotations01.csv")

# Convert Windows paths to current OS format
train_df['image_path'] = train_df['image_path'].str.replace('\\', '/')

# Load an image
def load_image(row):
    img_path = data_root / "train" / row['image_path']
    image = Image.open(img_path).convert('RGB')
    label = row['label']
    return image, label

# Example
image, label = load_image(train_df.iloc[0])
print(f"Label: {'Real' if label == 0 else 'Fake'}")

import torch
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms
import pandas as pd
from PIL import Image
from pathlib import Path

class TIGASDataset(Dataset):
    def __init__(self, root_dir, split='train', transform=None):
        self.root_dir = Path(root_dir)
        self.split = split
        self.transform = transform
        
        # Load annotations
        ann_path = self.root_dir / split / "annotations01.csv"
        self.annotations = pd.read_csv(ann_path)
        self.annotations['image_path'] = self.annotations['image_path'].str.replace('\\', '/')
        
        # Images are always in train/images/
        self.images_dir = self.root_dir / "train"
    
    def __len__(self):
        return len(self.annotations)
    
    def __getitem__(self, idx):
        row = self.annotations.iloc[idx]
        img_path = self.images_dir / row['image_path']
        image = Image.open(img_path).convert('RGB')
        label = row['label']
        
        if self.transform:
            image = self.transform(image)
        
        return image, label

# Example usage
transform = transforms.Compose([
    transforms.Resize((256, 256)),
    transforms.ToTensor(),
    transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
])

train_dataset = TIGASDataset("TIGAS", split='train', transform=transform)
test_dataset = TIGASDataset("TIGAS", split='test', transform=transform)

train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True, num_workers=4)
test_loader = DataLoader(test_dataset, batch_size=32, shuffle=False, num_workers=4)

from tigas import TIGAS

# Initialize model (auto-downloads from HuggingFace)
tigas = TIGAS(auto_download=True, device='cuda')

# Evaluate on dataset images
from pathlib import Path
import pandas as pd

data_root = Path("TIGAS")
test_df = pd.read_csv(data_root / "test" / "annotations01.csv")
test_df['image_path'] = test_df['image_path'].str.replace('\\', '/')

# Evaluate first 10 images
for i, row in test_df.head(10).iterrows():
    img_path = data_root / "train" / row['image_path']
    score = tigas(str(img_path))
    true_label = "Real" if row['label'] == 0 else "Fake"
    pred_label = "Real" if score > 0.5 else "Fake"
    print(f"{img_path.name}: Score={score:.4f}, True={true_label}, Pred={pred_label}")

@dataset{tigas_dataset_2025,
  title={TIGAS Dataset: A Comprehensive Collection for AI-Generated Image Detection},
  author={Morgenshtern, Dmitrij},
  year={2025},
  publisher={HuggingFace},
  url={https://huggingface.co/datasets/H1merka/TIGAS-dataset}
}