done

app.py

@@ -0,0 +1,42 @@
+import gradio as gr
+import numpy as np
+import os
+import zipfile
+from transformers import pipeline
+
+with zipfile.ZipFile("examples.zip","r") as zip_ref:
+    zip_ref.extractall(".")
+
+EXAMPLES_FOLDER = 'examples'
+examples_names = os.listdir(EXAMPLES_FOLDER)
+examples = []
+for example_name in examples_names:
+    example_path = os.path.join(EXAMPLES_FOLDER, example_name)
+    label = example_name.split('_')[0]
+    example = {
+        'path': example_path,
+        'label': label
+    }
+    examples.append(example)
+np.random.shuffle(examples)
+
+# Load the Hugging Face model
+model = pipeline("image-classification", model="dima806/deepfake_vs_real_image_detection", device="cuda")
+
+# Define the prediction function
+def classify_image(image):
+    results = model(image)
+    return {result['label']: result['score'] for result in results}
+
+# Create the Gradio interface
+interface = gr.Interface(
+    fn=classify_image,
+    inputs=gr.Image(type="pil"),  # Accepts images in PIL format
+    outputs=gr.Label(num_top_classes=2),  # Displays top two classifications with probabilities
+    title="Deepfake vs Real Image Detection",
+    description="Upload an image to determine whether it's real or deepfake.",
+    examples=[[examples[i]["path"], examples[i]["label"]] for i in range(10)]
+)
+
+# Launch the Gradio app
+interface.launch()

examples.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c719c2f16bad2e71d0d33d6ae59fa646dac82a812e1a90578c4b97ef6e8f36c
+size 28750945

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+Pillow
+pytorch
+transformers