Update app.py

app.py

@@ -68,16 +68,18 @@ def do_predict(pil_img: PIL.Image.Image):
     df = pandas.DataFrame({"image": [str(img_path)]})  # For AutoGluon expected input format
 
     try:
-        proba_df = PREDICTOR.predict_proba(df)  # For class probabilities
+        # For class probabilities
+        proba_df = PREDICTOR.predict_proba(df)  
+
         # For user-friendly column names
         proba_df = proba_df.rename(columns={0: "♻️ Recycling (0)", 1: "🗑️ Trash (1)"})
         row = proba_df.iloc[0]
+
         # For pretty ranked dict expected by gr.Label
         pretty_dict = {
             "♻️ Recycling": float(row.get("♻️ Recycling (0)", 0.0)),
             "🗑️ Trash": float(row.get("🗑️ Trash (1)", 0.0)),
         }
-        pretty_dict = dict(sorted(pretty_dict.items(), key=lambda kv: kv[1], reverse=True))
     except Exception:
         pretty_dict = {}
 
@@ -87,11 +89,20 @@ def do_predict(pil_img: PIL.Image.Image):
 EXAMPLES = [
     ["https://c8.alamy.com/comp/2AEA4K9/a-garbage-and-recycling-can-on-the-campus-of-carnegie-mellon-university-pittsburgh-pennsylvania-usa-2AEA4K9.jpg"], 
     ["https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSvid9M7DynMcoUsX0KBMxooLvrKQJwREiw6g&s"],  
+    ["https://cmccomb.com/assets/images/headshot_optimized_square.jpg"]
 ]
 
 # Gradio UI
 with gradio.Blocks() as demo:
 
+    # Provide an introduction
+    gradio.Markdown("# Trash or Recycling?")
+    gradio.Markdown("""
+    This is a simple app that demonstrates how to use an autogluon multimodal 
+    predictor in a gradio space to predict the contents of a picture. To use, 
+    just upload a photo. The result should be generated automatically.
+    """)
+    
     # Interface for the incoming image
     image_in = gradio.Image(type="pil", label="Input image", sources=["upload", "webcam"])