Update app.py

app.py

@@ -5,12 +5,15 @@ import numpy as np
 from PIL import Image
 import matplotlib.pyplot as plt
 
-# Load your trained model
-model = load_model("waste_classification(Mobilenetv2).h5")
+# Load model (ignore compile warning — you're only predicting)
+model = load_model("waste_classification(Mobilenetv2).h5", compile=False)
 class_names = ['cardboard', 'glass', 'metal', 'paper', 'plastic', 'trash']
 
-# Prediction function: returns label + chart
+# Prediction function: outputs label + chart
 def predict_with_chart(image):
+    if image is None:
+        return "No image received", None
+
     image = image.resize((224, 224))
     img_array = img_to_array(image) / 255.0
     img_array = np.expand_dims(img_array, axis=0)
@@ -20,7 +23,7 @@ def predict_with_chart(image):
     pred_label = class_names[pred_index]
     confidence = float(np.max(prediction))
 
-    # Plot bar chart
+    # Create bar chart
     fig, ax = plt.subplots(figsize=(6, 4))
     ax.bar(class_names, prediction, color='skyblue')
     ax.set_ylabel('Probability')
@@ -31,15 +34,15 @@ def predict_with_chart(image):
 
     return f"Prediction: {pred_label} ({confidence*100:.1f}%)", fig
 
-# Gradio interface: webcam + upload
-gr.Interface(
-    fn=predict_with_chart,
-    inputs=gr.Image(type="pil", label="Upload or Capture Waste Image", source="upload"),
-    outputs=[
-        gr.Textbox(label="Predicted Class"),
-        gr.Plot(label="Class Probability Chart")
-    ],
-    title="Waste Classifier - Upload or Webcam",
-    description="Upload a waste image or capture using webcam. The model shows predicted class and probability chart.",
-    live=True
-).launch()
+# Gradio Interface (Gradio 4.x compatible)
+with gr.Blocks() as demo:
+    gr.Markdown("## 🗑️ Waste Classifier — Upload or Capture an Image")
+    with gr.Row():
+        image_input = gr.Image(type="pil", label="Upload or Webcam (click camera icon)")
+    with gr.Row():
+        label_output = gr.Textbox(label="Predicted Class")
+        plot_output = gr.Plot(label="Class Probability Chart")
+
+    image_input.change(fn=predict_with_chart, inputs=image_input, outputs=[label_output, plot_output])
+
+demo.launch()