app.py

import gradio as gr
import torch
from PIL import Image
import os 
import yolov9

HTML_TEMPLATE = """
<style>
    body {
        background: linear-gradient(135deg, #1a2a6c, #b21f1f, #fdbb2d);
        font-family: 'Roboto', sans-serif;
        color: #ecf0f1;
        min-height: 100vh;
    }
    #app-header {
        text-align: center;
        background: rgba(26, 42, 108, 0.8);
        padding: 40px;
        border-radius: 20px;
        box-shadow: 0 15px 30px rgba(0, 0, 0, 0.4);
        position: relative;
        overflow: hidden;
        margin-bottom: 40px;
        backdrop-filter: blur(10px);
    }
    #app-header::before {
        content: "";
        position: absolute;
        top: -50%;
        left: -50%;
        width: 200%;
        height: 200%;
        background: radial-gradient(circle, rgba(253,187,45,0.2) 0%, rgba(253,187,45,0) 70%);
        animation: shimmer 20s infinite linear;
    }
    @keyframes shimmer {
        0% { transform: rotate(0deg); }
        100% { transform: rotate(360deg); }
    }
    #app-header h1 {
        color: #fdbb2d;
        font-size: 3em;
        margin-bottom: 20px;
        text-shadow: 2px 2px 4px rgba(0,0,0,0.3);
    }
    #app-header p {
        font-size: 1.3em;
        color: #ecf0f1;
    }
    .feature-container {
        display: flex;
        justify-content: center;
        gap: 40px;
        margin-top: 40px;
        flex-wrap: wrap;
    }
    .feature {
        position: relative;
        transition: all 0.4s ease;
        border-radius: 15px;
        overflow: hidden;
        background: rgba(178, 31, 31, 0.7);
        box-shadow: 0 8px 20px rgba(0,0,0,0.3);
        width: 180px;
        height: 180px;
        display: flex;
        flex-direction: column;
        justify-content: center;
        align-items: center;
    }
    .feature:hover {
        transform: translateY(-15px) rotate(5deg) scale(1.05);
        box-shadow: 0 20px 40px rgba(0,0,0,0.4);
        background: rgba(253, 187, 45, 0.8);
    }
    .feature-icon {
        font-size: 4em;
        color: #ecf0f1;
        margin-bottom: 15px;
        transition: all 0.4s ease;
    }
    .feature:hover .feature-icon {
        transform: scale(1.2);
    }
    .feature-description {
        color: #ecf0f1;
        font-size: 1em;
        text-align: center;
        padding: 0 10px;
        transition: all 0.4s ease;
    }
    .feature:hover .feature-description {
        font-weight: bold;
    }
    .artifact {
        position: absolute;
        background: radial-gradient(circle, rgba(253,187,45,0.3) 0%, rgba(253,187,45,0) 70%);
        border-radius: 50%;
        opacity: 0.5;
        filter: blur(40px);
    }
    .artifact.large {
        width: 600px;
        height: 600px;
        top: -200px;
        left: -300px;
        animation: float 30s infinite ease-in-out;
    }
    .artifact.medium {
        width: 400px;
        height: 400px;
        bottom: -200px;
        right: -200px;
        animation: float 25s infinite ease-in-out reverse;
    }
    .artifact.small {
        width: 200px;
        height: 200px;
        top: 50%;
        left: 50%;
        transform: translate(-50%, -50%);
        animation: pulse 8s infinite alternate;
    }
    @keyframes float {
        0%, 100% { transform: translateY(0) rotate(0deg); }
        50% { transform: translateY(-30px) rotate(15deg); }
    }
    @keyframes pulse {
        0% { transform: scale(1) translate(-50%, -50%); opacity: 0.5; }
        100% { transform: scale(1.2) translate(-50%, -50%); opacity: 0.8; }
    }
</style>
<div id="app-header">
    <div class="artifact large"></div>
    <div class="artifact medium"></div>
    <div class="artifact small"></div>
    <h1>YOLOv9: Manhole Detector</h1>
    <p>Unleash the power of AI to detect manholes with precision</p>
    <div class="feature-container">
        <div class="feature">
            <div class="feature-icon">🎯</div>
            <div class="feature-description">High Precision Detection</div>
        </div>
        <div class="feature">
            <div class="feature-icon">⚡</div>
            <div class="feature-description">Lightning-Fast Processing</div>
        </div>
        <div class="feature">
            <div class="feature-icon">🖼️</div>
            <div class="feature-description">Dynamic Image Resizing</div>
        </div>
        <div class="feature">
            <div class="feature-icon">🔧</div>
            <div class="feature-description">Fine-Tuned Thresholds</div>
        </div>
    </div>
</div>
"""

# The rest of the Python code remains the same
def yolov9_inference(img_path, image_size, conf_threshold, iou_threshold):
    model = yolov9.load('./best.pt') # Load your trained model
    model.conf = conf_threshold
    model.iou = iou_threshold
    results = model(img_path, size=image_size)
    output = results.render()
    return output[0]

def app():
    with gr.Blocks(theme=gr.themes.Soft()) as demo: # Added a theme here
        gr.HTML(HTML_TEMPLATE)
        
        with gr.Row():
            with gr.Column(scale=1, min_width=300):
                img_path = gr.Image(type="filepath", label="Upload Image")
                image_size = gr.Slider(label="Image Size", minimum=320, maximum=1280, step=32, value=640)
                conf_threshold = gr.Slider(label="Confidence Threshold", minimum=0.1, maximum=1.0, step=0.1, value=0.4)
                iou_threshold = gr.Slider(label="IoU Threshold", minimum=0.1, maximum=1.0, step=0.1, value=0.5)
                detect_button = gr.Button("Detect Manholes", variant="primary")
            
            with gr.Column(scale=1, min_width=300):
                output_numpy = gr.Image(type="numpy", label="Detection Result")
        
        detect_button.click(
            fn=yolov9_inference,
            inputs=[img_path, image_size, conf_threshold, iou_threshold],
            outputs=[output_numpy]
        )
        
        gr.Examples(
            examples=[
                ["./openmanhole.jpg", 640, 0.4, 0.5], # Add your example images
                ["./images.jpeg", 640, 0.4, 0.5],  # Add your example images
            ],
            fn=yolov9_inference,
            inputs=[img_path, image_size, conf_threshold, iou_threshold],
            outputs=[output_numpy],
            cache_examples=True,
        )
    
    return demo

# Removed the separate CSS variable and added theme to gr.Blocks

demo = gr.Blocks() # Moved the theme application here

with demo:
    app()

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