Ai Vs Human Image Detector

🚀 AI與人類圖像分類模型

本項目是一個經過微調的圖像分類模型，在60,000張AI生成圖像和60,000張人類圖像上進行訓練。該模型能夠出色地檢測出由Midjourney v6.1、Flux 1.1 Pro、Stable Diffusion 3.5、GPT - 4o等前沿AI模型生成的高質量圖像。

詳細的訓練代碼可查看：blog/ai/fine - tuning - siglip2

🚀 快速開始

安裝依賴

pip install -q transformers torch Pillow accelerate

代碼示例

import torch
from PIL import Image as PILImage
from transformers import AutoImageProcessor, SiglipForImageClassification

MODEL_IDENTIFIER = r"Ateeqq/ai-vs-human-image-detector"

# Device: Use GPU if available, otherwise CPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f"Using device: {device}")

# Load Model and Processor
try:
    print(f"Loading processor from: {MODEL_IDENTIFIER}")
    processor = AutoImageProcessor.from_pretrained(MODEL_IDENTIFIER)

    print(f"Loading model from: {MODEL_IDENTIFIER}")
    model = SiglipForImageClassification.from_pretrained(MODEL_IDENTIFIER)
    model.to(device)
    model.eval()
    print("Model and processor loaded successfully.")

except Exception as e:
    print(f"Error loading model or processor: {e}")
    exit()

# Load and Preprocess the Image

IMAGE_PATH = r"/content/images.jpg" 
try:
    print(f"Loading image: {IMAGE_PATH}")
    image = PILImage.open(IMAGE_PATH).convert("RGB")
except FileNotFoundError:
    print(f"Error: Image file not found at {IMAGE_PATH}")
    exit()
except Exception as e:
    print(f"Error opening image: {e}")
    exit()

print("Preprocessing image...")
# Use the processor to prepare the image for the model
inputs = processor(images=image, return_tensors="pt").to(device)

# Perform Inference
print("Running inference...")
with torch.no_grad(): # Disable gradient calculations for inference
    outputs = model(**inputs)
    logits = outputs.logits

# Interpret the Results
# Get the index of the highest logit score -> this is the predicted class ID
predicted_class_idx = logits.argmax(-1).item()

# Use the model's config to map the ID back to the label string ('ai' or 'hum')
predicted_label = model.config.id2label[predicted_class_idx]

# Optional: Get probabilities using softmax
probabilities = torch.softmax(logits, dim=-1)
predicted_prob = probabilities[0, predicted_class_idx].item()

print("-" * 30)
print(f"Image: {IMAGE_PATH}")
print(f"Predicted Label: {predicted_label}")
print(f"Confidence Score: {predicted_prob:.4f}")
print("-" * 30)

# You can also print the scores for all classes:
print("Scores per class:")
for i, label in model.config.id2label.items():
    print(f"  - {label}: {probabilities[0, i].item():.4f}")

輸出示例

Using device: cpu
Model and processor loaded successfully.
Loading image: /content/images.jpg
Preprocessing image...
Running inference...
------------------------------
Image: /content/images.jpg
Predicted Label: ai
Confidence Score: 0.9996
------------------------------
Scores per class:
  - ai: 0.9996
  - hum: 0.0004

✨ 主要特性

• 強大的檢測能力：能夠有效識別多種前沿AI模型生成的高質量圖像。
• 高準確率：在測試集上取得了高達0.9923的準確率。

📚 詳細文檔

評估指標

🏋️‍♂️ 訓練指標

• Epoch：5.0
• 總浮點運算次數（Total FLOPs）：51,652,280,821 GF
• 訓練損失（Train Loss）：0.0799
• 訓練運行時間（Train Runtime）：2:39:49.46
• 訓練樣本每秒處理數（Train Samples/Sec）：69.053
• 訓練步驟每秒處理數（Train Steps/Sec）：4.316

📊 評估指標（微調模型在測試集上）

• Epoch：5.0
• 評估準確率（Eval Accuracy）：0.9923
• 評估損失（Eval Loss）：0.0551
• 評估運行時間（Eval Runtime）：0:02:35.78
• 評估樣本每秒處理數（Eval Samples/Sec）：212.533
• 評估步驟每秒處理數（Eval Steps/Sec）：6.644

🔦 預測指標（在測試集上）

{
  "test_loss": 0.05508904904127121,
  "test_accuracy": 0.9923283699296264,
  "test_runtime": 167.1844,
  "test_samples_per_second": 198.039,
  "test_steps_per_second": 6.191
}

• 最終測試準確率：0.9923
• 最終測試F1分數（Macro）：0.9923
• 最終測試F1分數（Weighted）：0.9923

📄 許可證

本項目採用Apache - 2.0許可證。