app.py

import gradio as gr
import numpy as np
from PIL import Image
import tensorflow as tf


model = tf.keras.models.load_model("Educell_Garbage.keras", compile=False)


class_names = ['cardboard', 'glass', 'metal', 'paper', 'plastic', 'trash']


def classify_image(img):
    img = img.resize((124, 124))
    img_array = np.array(img, dtype=np.float32)
    img_array = np.expand_dims(img_array, axis=0)
    prediction = model.predict(img_array)[0]
    predicted_class = class_names[np.argmax(prediction)]
    confidence = float(np.max(prediction)) * 100

    return f"📁 **Predicted Class:** `{predicted_class.upper()}`\n🎯 **Confidence:** `{confidence:.2f}%`"

# Dark mode CSS
custom_css = """
body, .gradio-container {
    background-color: #1f1f1f !important;
    color: #f2f2f2 !important;
    font-family: 'Segoe UI', sans-serif;
}
#output_textbox {
    background-color: #2b2b2b !important;
    color: #ffffff !important;
    padding: 20px;
    border-radius: 12px;
    box-shadow: 0 4px 10px rgba(0, 0, 0, 0.3);
    font-size: 18px;
    font-weight: 500;
}
h1, .gr-markdown {
    text-align: center;
    color: #00ffcc !important;
}
"""

# Interface layout
with gr.Blocks(css=custom_css) as demo:
    gr.Markdown("## ♻️ Garbage Classification AI")
    gr.Markdown("Upload an image of waste and the AI will classify it as **Plastic**, **Glass**, **Paper**, etc.")

    with gr.Row():
        with gr.Column(scale=1):
            image_input = gr.Image(label="Upload Image", type="pil", height=300)
            submit_btn = gr.Button("🔍 Classify", size="lg")

        with gr.Column(scale=1):
            prediction_output = gr.Markdown(elem_id="output_textbox", show_label=False)

    submit_btn.click(fn=classify_image, inputs=image_input, outputs=prediction_output)

    gr.Markdown("---")
    gr.Markdown("Made with ❤️ for smart waste segregation")

if __name__ == "__main__":
    demo.launch(share=True)