Create app.py

app.py

@@ -0,0 +1,44 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+import os
+
+# Get the API token from environment variables
+api_token = os.getenv("HUGGINGFACE_API_TOKEN")
+
+# Initialize the Inference Client for your model
+client = InferenceClient(
+    model="SerdarHelli/Segmentation-of-Teeth-in-Panoramic-X-ray-Image-Using-U-Net",
+    token=api_token
+)
+
+def predict(image):
+    """
+    Process the uploaded image and return the segmentation result.
+    
+    Args:
+        image: PIL Image object from Gradio input
+    
+    Returns:
+        The segmentation result (assumed to be an image) or an error message
+    """
+    try:
+        # TODO: Add any necessary preprocessing here (e.g., resizing, normalization)
+        # Send the image to the model via the Inference API
+        result = client.post(data={"inputs": image})
+        # TODO: Add any necessary postprocessing here (e.g., converting to image, overlaying on original)
+        # For now, assuming the result is directly the segmentation image
+        return result
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil", label="Upload Panoramic X-ray Image"),
+    outputs=gr.Image(type="pil", label="Segmentation Result"),
+    title="Teeth Segmentation in Panoramic X-rays",
+    description="Upload an X-ray image to see the segmented teeth."
+)
+
+# Launch the interface
+iface.launch()