alianassmaaa/multimodal-deepfake-detector

Visual Branch    EfficientNet-B0/B4  ──┐
                                       ├──► Fusion pondérée ──► Confidence [0-1]
Text Branch      RoBERTa-base         ──┘
                    ↓
               GradCAM Heatmap (explicabilité)

from inference import load_model, classify_image, classify_text, classify_multimodal

model, config = load_model('multimodal_ensemble.pt', device='cuda')

# Image + GradCAM
result = classify_image(model, 'face.jpg', return_gradcam=True)
print(f"{result['prediction']} — confidence: {result['confidence']:.2%}")
# result['gradcam'] → heatmap (224, 224)

# Texte
result = classify_text(model, 'Cet essai analyse les impacts...')
print(f"{result['prediction']} — confidence: {result['confidence']:.2%}")

# Multimodal (image + texte)
result = classify_multimodal(model, image_path_or_pil='face.jpg', text='Caption...')
print(f"Fusion: {result['prediction']} — poids: {result['fusion_weights']}")