Update deepfake_vs_real.py

deepfake_vs_real.py

@@ -1,36 +1,39 @@
 import gradio as gr
 import spaces
-from transformers import ViTForImageClassification, ViTImageProcessor
+from transformers import AutoImageProcessor
+from transformers import SiglipForImageClassification
+from transformers.image_utils import load_image
 from PIL import Image
 import torch
 
-# Load the model and processor
-model_name = "prithivMLmods/Deep-Fake-Detector-v2-Model"
-model = ViTForImageClassification.from_pretrained(model_name)
-processor = ViTImageProcessor.from_pretrained(model_name)
+# Load model and processor
+model_name = "prithivMLmods/Deepfake-Detect-Siglip2"
+model = SiglipForImageClassification.from_pretrained(model_name)
+processor = AutoImageProcessor.from_pretrained(model_name)
 
 @spaces.GPU
-def deepfake_classification(image):
-    """Predicts whether an image is a Deepfake or Real."""
+def deepfake_detection(image):
+    """Classifies an image as Fake or Real."""
     image = Image.fromarray(image).convert("RGB")
     inputs = processor(images=image, return_tensors="pt")
     
     with torch.no_grad():
         outputs = model(**inputs)
         logits = outputs.logits
-        predicted_class = torch.argmax(logits, dim=1).item()
+        probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist()
     
-    # Get label mapping
-    label = model.config.id2label[predicted_class] if hasattr(model.config, "id2label") else str(predicted_class)
-    return {label: 1.0}  # Gradio Label output expects a dictionary
+    labels = model.config.id2label
+    predictions = {labels[i]: round(probs[i], 3) for i in range(len(probs))}
+    
+    return predictions
 
 # Create Gradio interface
 iface = gr.Interface(
-    fn=deepfake_classification,
+    fn=deepfake_detection,
     inputs=gr.Image(type="numpy"),
-    outputs=gr.Label(label="Prediction"),
-    title="Deepfake vs. Real Image Classification",
-    description="Upload an image to determine if it's a Deepfake or a Real one."
+    outputs=gr.Label(label="Detection Result"),
+    title="Deepfake Detection Model",
+    description="Upload an image to determine if it is Fake or Real."
 )
 
 # Launch the app