Update app.py

app.py

@@ -4,16 +4,14 @@ from tensorflow.keras.preprocessing.image import img_to_array
 import numpy as np
 from PIL import Image
 
-# 🔹 Load your saved model
-model = load_model("waste_classification(Mobilenetv2).h5")
-
-# 🔹 Define your class labels (must match model training)
+# Load model
+model = load_model("waste_classifier_model.h5")
 class_names = ['cardboard', 'glass', 'metal', 'paper', 'plastic', 'trash']
 
-# 🔹 Prediction function
-def predict_from_camera(image):
-    image = image.resize((224, 224))  # Resize for model input
-    img_array = img_to_array(image) / 255.0  # Normalize
+# Prediction function
+def predict_from_webcam(image):
+    image = image.resize((224, 224))
+    img_array = img_to_array(image) / 255.0
     img_array = np.expand_dims(img_array, axis=0)
 
     prediction = model.predict(img_array)[0]
@@ -22,13 +20,13 @@ def predict_from_camera(image):
 
     return f"{predicted_class} ({confidence*100:.1f}%)"
 
-# 🔹 Gradio live webcam interface
+# Use gr.Camera instead of gr.Image
 interface = gr.Interface(
-    fn=predict_from_camera,
-    inputs=gr.Image(source="webcam", streaming=True, type="pil"),
+    fn=predict_from_webcam,
+    inputs=gr.Camera(type="pil"),
     outputs="text",
-    title="Live Waste Classification",
-    description="Show waste to your webcam and the model will predict its type in real-time."
+    title="Live Waste Classifier",
+    description="Point your webcam at a waste item. The model will predict its type in real-time."
 )
 
 interface.launch()