Update app.py

app.py

@@ -1,33 +1,11 @@
 import gradio as gr
-from PIL import Image
-import numpy as np
-
-def predict(image):
-    try:
-        # Ensure the input is a PIL Image
-        if isinstance(image, np.ndarray):
-            # Convert numpy array to PIL Image
-            image = Image.fromarray(image)
-        
-        if not isinstance(image, Image.Image):
-            return {"error": "Input is not a valid image"}
-        
-        # Perform your prediction here
-        # Placeholder for actual prediction logic
-        result = {"Disease": "Predicted Disease", "Confidence": 0.95}
-        return result
-
-    except Exception as e:
-        return {"error": str(e)}
-
-interface = gr.Interface(
-    fn=predict,
-    inputs=gr.Image(type="numpy"),  # Use 'numpy' type for better compatibility
-    outputs=gr.Label(num_top_classes=3),
-    examples=[["MoucheB.jpg"], ["verdissement.jpg"]],
-    title="Orange Disease Detector",
-    description="Detect diseases in orange leaves and fruits."
-)
-
-if __name__ == "__main__":
-    interface.launch()
+from transformers import pipeline
+
+pipe = pipeline(task="image-classification", 
+                # model that can do 22k-category classification
+                model="KhadijaAsehnoune12/orange-disease-detector")
+gr.Interface.from_pipeline(pipe, 
+                           title="22k Image Classification",
+                           description="Detect diseases in orange leaves and fruits.",
+                           examples = ['MoucheB.jpg', 'verdissement.jpg',],
+                           ).launch()