Upload app.py

app.py

@@ -0,0 +1,131 @@
+import gradio as gr
+import numpy as np
+from PIL import Image
+from tensorflow.keras.models import load_model
+from tensorflow.keras.applications.efficientnet import preprocess_input as efficientnet_preprocess
+import pandas as pd
+import os
+from datetime import datetime
+
+# Waste classes
+class_names = ['BATTERIES', 'CLOTHES', 'E-WASTE', 'GLASS', 'LIGHT-BULBS', 'METAL', 'ORGANIC', 'PAPER', 'PLASTIC']
+
+# Advice dictionary
+waste_advice = {
+    "PAPER": "Recycle clean paper. Avoid recycling greasy or food-stained paper.",
+    "CLOTHES": "Donate if usable. Otherwise, check textile recycling centres.",
+    "BATTERIES": "Take to hazardous waste collection or battery drop-off locations.",
+    "GLASS": "Rinse and recycle glass containers separately from ceramics.",
+    "PLASTIC": "Recycle plastics labelled with numbers 1 and 2. Check local rules for others.",
+    "ORGANIC": "Compost organic waste like food scraps and garden waste.",
+    "LIGHT-BULBS": "Take to a special collection point for bulbs and fluorescents.",
+    "E-WASTE": "Recycle at designated e-waste centres or electronics stores.",
+    "METAL": "Recycle metals in designated metal bins. Rinse before disposal."
+}
+
+# Load model with error handling
+try:
+    model = load_model("model_efnet.keras")
+    print("Model loaded successfully!")
+except FileNotFoundError:
+    print("Error: 'model_efnet.keras' not found. Please upload the model file.")
+    model = None
+
+img_size = (224, 224)
+
+# CSV for logging predictions and feedback
+log_file = "prediction_log.csv"
+if not os.path.exists(log_file):
+    pd.DataFrame(columns=["Timestamp", "Prediction", "Confidence", "Feedback"]).to_csv(log_file, index=False)
+
+# Prediction function
+def predict(image):
+    if model is None:
+        return "Error: Model not loaded.", "", None, None, {}
+    
+    img = image.convert("RGB").resize(img_size)
+    img_array = np.array(img)
+    img_array = efficientnet_preprocess(img_array)
+    img_array = np.expand_dims(img_array, axis=0)
+
+    prediction = model.predict(img_array)[0]
+    predicted_index = np.argmax(prediction)
+    predicted_class = class_names[predicted_index]
+    confidence = prediction[predicted_index]
+
+    result = f" {predicted_class} ( Probability {confidence:.2f})"
+    probabilities = {class_names[i]: float(prediction[i]) for i in range(len(class_names))}
+    advice = waste_advice.get(predicted_class, "No advice available.")
+
+    return result, advice, predicted_class, confidence, probabilities
+
+# Feedback function
+def save_feedback(predicted_class, confidence, feedback):
+    timestamp = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+    df = pd.read_csv(log_file)
+    new_row = pd.DataFrame({
+        "Timestamp": [timestamp],
+        "Prediction": [predicted_class],
+        "Confidence": [round(confidence, 2)],
+        "Feedback": [feedback]
+    })
+    df = pd.concat([df, new_row], ignore_index=True)
+    df.to_csv(log_file, index=False)
+    return "Feedback saved. Thank you!"
+
+# Handle feedback visibility
+def handle_feedback(feedback):
+    if feedback == "👎":
+        return gr.update(visible=True), gr.update(visible=True), ""
+    else:
+        return gr.update(visible=False), gr.update(visible=False), "✅ Thank you"
+
+# Clear all
+def clear_all():
+    return None, "", "", None, None, {}, None, gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## ♻️ Waste Management Classifier")
+
+    with gr.Row():
+        image_input = gr.Image(label="Upload or Use Webcam", sources=["upload", "webcam"], type="pil")
+        with gr.Column():
+            result = gr.Label(label="Prediction")
+            advice_output = gr.Textbox(label="Waste Disposal Advice", lines=2)
+    
+    pred_class = gr.State()
+    pred_conf = gr.State()
+    probabilities = gr.State()
+
+    with gr.Row():
+        predict_button = gr.Button("Predict")
+        clear_btn = gr.Button("Clear")
+    
+    predict_button.click(
+        fn=predict,
+        inputs=image_input,
+        outputs=[result, advice_output, pred_class, pred_conf, probabilities]
+    )
+
+    gr.Markdown("### How accurate was the prediction?")
+    with gr.Row():
+        thumbs = gr.Radio(["👍", "👎"], label="Prediction Status")
+        feedback_box = gr.Textbox(lines=2, placeholder="What should the model have predicted?", visible=False, label="Your Feedback")
+        submit_feedback = gr.Button("Submit Feedback", visible=False)
+        feedback_ack = gr.Textbox(visible=False, label="", interactive=False)
+
+    clear_btn.click(
+        fn=clear_all,
+        outputs=[image_input, result, advice_output, pred_class, pred_conf, probabilities, thumbs, feedback_box, submit_feedback, feedback_ack]
+    )
+    thumbs.change(
+        fn=handle_feedback,
+        inputs=[thumbs],
+        outputs=[feedback_box, submit_feedback, feedback_ack]
+    )
+    submit_feedback.click(
+        fn=save_feedback,
+        inputs=[pred_class, pred_conf, feedback_box],
+        outputs=feedback_ack
+    )