Update app.py

app.py

@@ -1,30 +1,30 @@
 import gradio as gr
 from PIL import Image
-import requests
+import numpy as np
 
 # Load the pre-trained model from Hugging Face
 model = gr.load("models/dima806/indian_food_image_detection")
 
 def classify_image(image):
-    # Convert PIL image to the format expected by the model
-    image = Image.fromarray(image)
+    # Ensure the image is in the correct format for the model
+    if isinstance(image, np.ndarray):
+        image = Image.fromarray(image)
     result = model(image)
     
     # Parse the result to the format expected by Gradio's label component
-    predictions = result[0]["labels"]  # Adjust this line based on the actual output structure
+    predictions = result[0]  # Adjust this line based on the actual output structure
     formatted_result = {pred["label"]: pred["score"] for pred in predictions}
-    
+
     return formatted_result
 
 # Create a Gradio interface with the custom title
 iface = gr.Interface(
     fn=classify_image, 
-    inputs=gr.Image(type="numpy"), 
-    outputs=gr.Label(), 
+    inputs=gr.Image(type="numpy", label="Upload an image"), 
+    outputs=gr.Label(label="Prediction"), 
     title="CAPSTONE",
-    description="Upload an image of Indian food to detect what it is.",
-    live=True  # Enable live processing
+    description="Upload an image of Indian food to detect what it is."
 )
 
 # Launch the Gradio interface
-iface.launch(share=True)
+iface.launch()