Update app.py

app.py

@@ -1,414 +1,416 @@
 
-import streamlit as st
-from PIL import Image
-import torch
-import cv2
-import numpy as np
-from datetime import datetime
-import plotly.express as px
-import plotly.graph_objects as go
-import pandas as pd
-from ultralytics import YOLO
-import os
-import io
-from fpdf import FPDF
-import base64
+# import streamlit as st
+# from PIL import Image
+# import torch
+# import cv2
+# import numpy as np
+# from datetime import datetime
+# import plotly.express as px
+# import plotly.graph_objects as go
+# import pandas as pd
+# from ultralytics import YOLO
+# import os
+# import io
+# from fpdf import FPDF
+# import base64
 
-# Page config
-st.set_page_config(
-    page_title="Traffic Sign Detection System",
-    page_icon="🚦",
-    layout="wide",
-    initial_sidebar_state="expanded"
-)
+# # Page config
+# st.set_page_config(
+#     page_title="Traffic Sign Detection System",
+#     page_icon="🚦",
+#     layout="wide",
+#     initial_sidebar_state="expanded"
+# )
 
-# Custom CSS
-st.markdown("""
-    <style>
-    .stApp {
-        background: linear-gradient(135deg, #1a1a2e 0%, #16213e 100%);
-        color: #e5e5e5;
-    }
-    .upload-box {
-        border: 2px dashed #4a4a8a;
-        border-radius: 15px;
-        padding: 30px;
-        text-align: center;
-        background: rgba(255,255,255,0.05);
-        backdrop-filter: blur(10px);
-        transition: all 0.3s ease;
-    }
-    .upload-box:hover {
-        border-color: #6a6aaa;
-        background: rgba(255,255,255,0.08);
-    }
-    .detection-box {
-        background: rgba(255,255,255,0.07);
-        padding: 25px;
-        border-radius: 15px;
-        margin: 15px 0;
-        box-shadow: 0 4px 15px rgba(0,0,0,0.2);
-    }
-    .metrics-card {
-        background: rgba(255,255,255,0.1);
-        padding: 20px;
-        border-radius: 10px;
-        margin: 10px 0;
-        transition: transform 0.3s ease;
-    }
-    .metrics-card:hover {
-        transform: translateY(-5px);
-    }
-    .confidence-meter {
-        height: 20px;
-        background: rgba(255,255,255,0.1);
-        border-radius: 10px;
-        overflow: hidden;
-        box-shadow: inset 0 0 5px rgba(0,0,0,0.2);
-    }
-    .header-container {
-        padding: 20px;
-        background: rgba(255,255,255,0.05);
-        border-radius: 15px;
-        margin-bottom: 20px;
-        text-align: center;
-    }
-    .stButton>button {
-        background: linear-gradient(45deg, #3498db, #2980b9);
-        color: white;
-        border: none;
-        padding: 10px 20px;
-        border-radius: 8px;
-        transition: all 0.3s ease;
-    }
-    .stButton>button:hover {
-        transform: translateY(-2px);
-        box-shadow: 0 5px 15px rgba(0,0,0,0.2);
-    }
-    </style>
-""", unsafe_allow_html=True)
+# # Custom CSS
+# st.markdown("""
+#     <style>
+#     .stApp {
+#         background: linear-gradient(135deg, #1a1a2e 0%, #16213e 100%);
+#         color: #e5e5e5;
+#     }
+#     .upload-box {
+#         border: 2px dashed #4a4a8a;
+#         border-radius: 15px;
+#         padding: 30px;
+#         text-align: center;
+#         background: rgba(255,255,255,0.05);
+#         backdrop-filter: blur(10px);
+#         transition: all 0.3s ease;
+#     }
+#     .upload-box:hover {
+#         border-color: #6a6aaa;
+#         background: rgba(255,255,255,0.08);
+#     }
+#     .detection-box {
+#         background: rgba(255,255,255,0.07);
+#         padding: 25px;
+#         border-radius: 15px;
+#         margin: 15px 0;
+#         box-shadow: 0 4px 15px rgba(0,0,0,0.2);
+#     }
+#     .metrics-card {
+#         background: rgba(255,255,255,0.1);
+#         padding: 20px;
+#         border-radius: 10px;
+#         margin: 10px 0;
+#         transition: transform 0.3s ease;
+#     }
+#     .metrics-card:hover {
+#         transform: translateY(-5px);
+#     }
+#     .confidence-meter {
+#         height: 20px;
+#         background: rgba(255,255,255,0.1);
+#         border-radius: 10px;
+#         overflow: hidden;
+#         box-shadow: inset 0 0 5px rgba(0,0,0,0.2);
+#     }
+#     .header-container {
+#         padding: 20px;
+#         background: rgba(255,255,255,0.05);
+#         border-radius: 15px;
+#         margin-bottom: 20px;
+#         text-align: center;
+#     }
+#     .stButton>button {
+#         background: linear-gradient(45deg, #3498db, #2980b9);
+#         color: white;
+#         border: none;
+#         padding: 10px 20px;
+#         border-radius: 8px;
+#         transition: all 0.3s ease;
+#     }
+#     .stButton>button:hover {
+#         transform: translateY(-2px);
+#         box-shadow: 0 5px 15px rgba(0,0,0,0.2);
+#     }
+#     </style>
+# """, unsafe_allow_html=True)
 
-# Initialize session state
-if 'model' not in st.session_state:
-    st.session_state.model = None
-    st.session_state.total_analyses = 0
+# # Initialize session state
+# if 'model' not in st.session_state:
+#     st.session_state.model = None
+#     st.session_state.total_analyses = 0
 
-@st.cache_resource
-def load_model():
-    """Load and cache the YOLO model"""
-    try:
-        model = YOLO('best.pt')
-        return model
-    except Exception as e:
-        st.error(f"Error loading model: {str(e)}")
-        return None
+# @st.cache_resource
+# def load_model():
+#     """Load and cache the YOLO model"""
+#     try:
+#         model = YOLO('best.pt')
+#         return model
+#     except Exception as e:
+#         st.error(f"Error loading model: {str(e)}")
+#         return None
 
-def create_confidence_bar(confidence):
-    """Create a visual confidence meter"""
-    colors = {
-        "high": "#00ff00",
-        "medium": "#ffaa00",
-        "low": "#ff0000"
-    }
-    color = colors["high"] if confidence > 0.7 else colors["medium"] if confidence > 0.5 else colors["low"]
-    return f"""
-        <div class="confidence-meter">
-            <div style="width:{confidence*100}%; height:100%; background:{color}; 
-                 transition:width 0.5s; text-align:center; color:white; line-height:20px;">
-                {confidence:.1%}
-            </div>
-        </div>
-    """
+# def create_confidence_bar(confidence):
+#     """Create a visual confidence meter"""
+#     colors = {
+#         "high": "#00ff00",
+#         "medium": "#ffaa00",
+#         "low": "#ff0000"
+#     }
+#     color = colors["high"] if confidence > 0.7 else colors["medium"] if confidence > 0.5 else colors["low"]
+#     return f"""
+#         <div class="confidence-meter">
+#             <div style="width:{confidence*100}%; height:100%; background:{color}; 
+#                  transition:width 0.5s; text-align:center; color:white; line-height:20px;">
+#                 {confidence:.1%}
+#             </div>
+#         </div>
+#     """
 
-def create_visualization(results, model):
-    """Create visualization plots for detection results"""
-    if len(results.boxes) > 0:
-        # Prepare data for visualization
-        confidences = results.boxes.conf.cpu().numpy()
-        classes = [model.names[int(cls)] for cls in results.boxes.cls.cpu().numpy()]
+# def create_visualization(results, model):
+#     """Create visualization plots for detection results"""
+#     if len(results.boxes) > 0:
+#         # Prepare data for visualization
+#         confidences = results.boxes.conf.cpu().numpy()
+#         classes = [model.names[int(cls)] for cls in results.boxes.cls.cpu().numpy()]
         
-        # Create confidence distribution plot
-        fig_conf = go.Figure(data=[go.Histogram(x=confidences, nbinsx=20)])
-        fig_conf.update_layout(
-            title="Confidence Score Distribution",
-            xaxis_title="Confidence Score",
-            yaxis_title="Count",
-            template="plotly_dark"
-        )
+#         # Create confidence distribution plot
+#         fig_conf = go.Figure(data=[go.Histogram(x=confidences, nbinsx=20)])
+#         fig_conf.update_layout(
+#             title="Confidence Score Distribution",
+#             xaxis_title="Confidence Score",
+#             yaxis_title="Count",
+#             template="plotly_dark"
+#         )
         
-        # Create class distribution plot
-        class_counts = pd.Series(classes).value_counts()
-        fig_class = px.pie(values=class_counts.values, names=class_counts.index,
-                          title="Distribution of Detected Signs")
-        fig_class.update_layout(template="plotly_dark")
+#         # Create class distribution plot
+#         class_counts = pd.Series(classes).value_counts()
+#         fig_class = px.pie(values=class_counts.values, names=class_counts.index,
+#                           title="Distribution of Detected Signs")
+#         fig_class.update_layout(template="plotly_dark")
         
-        return fig_conf, fig_class
-    return None, None
+#         return fig_conf, fig_class
+#     return None, None
 
-class PDF(FPDF):
-    def header(self):
-        self.set_font('Arial', 'B', 20)
-        self.cell(0, 10, 'Traffic Sign Detection Report', 0, 1, 'C')
-        self.ln(10)
+# class PDF(FPDF):
+#     def header(self):
+#         self.set_font('Arial', 'B', 20)
+#         self.cell(0, 10, 'Traffic Sign Detection Report', 0, 1, 'C')
+#         self.ln(10)
         
-    def footer(self):
-        self.set_y(-15)
-        self.set_font('Arial', 'I', 8)
-        self.cell(0, 10, f'Report generated on {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}', 0, 0, 'C')
-
-def generate_pdf_report(original_image, detected_image, results, model, analytics_enabled=True):
-    """Generate a PDF report with detection results and analytics"""
-    pdf = PDF()
-    pdf.add_page()
-    
-    # Add timestamp
-    pdf.set_font('Arial', '', 12)
-    pdf.cell(0, 10, f'Analysis Date: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}', 0, 1)
-    pdf.ln(5)
-    
-    # Save and add images
-    # Original Image
-    pdf.set_font('Arial', 'B', 14)
-    pdf.cell(0, 10, 'Original Image', 0, 1)
-    
-    # Convert original image to RGB if needed
-    if len(original_image.shape) == 3 and original_image.shape[2] == 3:
-        original_image_rgb = cv2.cvtColor(original_image, cv2.COLOR_BGR2RGB)
-    else:
-        original_image_rgb = original_image
+#     def footer(self):
+#         self.set_y(-15)
+#         self.set_font('Arial', 'I', 8)
+#         self.cell(0, 10, f'Report generated on {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}', 0, 0, 'C')
+
+# def generate_pdf_report(original_image, detected_image, results, model, analytics_enabled=True):
+#     """Generate a PDF report with detection results and analytics"""
+#     pdf = PDF()
+#     pdf.add_page()
+    
+#     # Add timestamp
+#     pdf.set_font('Arial', '', 12)
+#     pdf.cell(0, 10, f'Analysis Date: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}', 0, 1)
+#     pdf.ln(5)
+    
+#     # Save and add images
+#     # Original Image
+#     pdf.set_font('Arial', 'B', 14)
+#     pdf.cell(0, 10, 'Original Image', 0, 1)
+    
+#     # Convert original image to RGB if needed
+#     if len(original_image.shape) == 3 and original_image.shape[2] == 3:
+#         original_image_rgb = cv2.cvtColor(original_image, cv2.COLOR_BGR2RGB)
+#     else:
+#         original_image_rgb = original_image
         
-    # Save original image
-    orig_img_path = 'temp_original.jpg'
-    cv2.imwrite(orig_img_path, cv2.cvtColor(original_image_rgb, cv2.COLOR_RGB2BGR))
-    pdf.image(orig_img_path, x=10, w=190)
-    pdf.ln(10)
-    
-    # Detection Results
-    pdf.set_font('Arial', 'B', 14)
-    pdf.cell(0, 10, 'Detection Results', 0, 1)
-    
-    # Save detected image
-    detected_img_path = 'temp_detected.jpg'
-    cv2.imwrite(detected_img_path, cv2.cvtColor(detected_image, cv2.COLOR_RGB2BGR))
-    pdf.image(detected_img_path, x=10, w=190)
-    pdf.ln(10)
-    
-    # Detection Details
-    pdf.set_font('Arial', 'B', 14)
-    pdf.cell(0, 10, 'Detection Details', 0, 1)
-    pdf.set_font('Arial', '', 12)
+#     # Save original image
+#     orig_img_path = 'temp_original.jpg'
+#     cv2.imwrite(orig_img_path, cv2.cvtColor(original_image_rgb, cv2.COLOR_RGB2BGR))
+#     pdf.image(orig_img_path, x=10, w=190)
+#     pdf.ln(10)
+    
+#     # Detection Results
+#     pdf.set_font('Arial', 'B', 14)
+#     pdf.cell(0, 10, 'Detection Results', 0, 1)
+    
+#     # Save detected image
+#     detected_img_path = 'temp_detected.jpg'
+#     cv2.imwrite(detected_img_path, cv2.cvtColor(detected_image, cv2.COLOR_RGB2BGR))
+#     pdf.image(detected_img_path, x=10, w=190)
+#     pdf.ln(10)
+    
+#     # Detection Details
+#     pdf.set_font('Arial', 'B', 14)
+#     pdf.cell(0, 10, 'Detection Details', 0, 1)
+#     pdf.set_font('Arial', '', 12)
     
-    if len(results.boxes) > 0:
-        # Summary statistics
-        avg_conf = float(torch.mean(results.boxes.conf).item())
-        unique_classes = len(set(results.boxes.cls.cpu().numpy()))
+#     if len(results.boxes) > 0:
+#         # Summary statistics
+#         avg_conf = float(torch.mean(results.boxes.conf).item())
+#         unique_classes = len(set(results.boxes.cls.cpu().numpy()))
         
-        pdf.cell(0, 10, f'Total Detections: {len(results.boxes)}', 0, 1)
-        pdf.cell(0, 10, f'Average Confidence: {avg_conf:.2%}', 0, 1)
-        pdf.cell(0, 10, f'Unique Sign Types: {unique_classes}', 0, 1)
-        pdf.ln(5)
+#         pdf.cell(0, 10, f'Total Detections: {len(results.boxes)}', 0, 1)
+#         pdf.cell(0, 10, f'Average Confidence: {avg_conf:.2%}', 0, 1)
+#         pdf.cell(0, 10, f'Unique Sign Types: {unique_classes}', 0, 1)
+#         pdf.ln(5)
         
-        # Detailed detections
-        pdf.set_font('Arial', 'B', 12)
-        pdf.cell(0, 10, 'Detailed Detections:', 0, 1)
-        pdf.set_font('Arial', '', 12)
+#         # Detailed detections
+#         pdf.set_font('Arial', 'B', 12)
+#         pdf.cell(0, 10, 'Detailed Detections:', 0, 1)
+#         pdf.set_font('Arial', '', 12)
         
-        for idx, box in enumerate(results.boxes):
-            class_id = int(box.cls[0])
-            conf = float(box.conf[0])
-            class_name = model.names[class_id]
-            box_coords = box.xyxy[0].cpu().numpy()
+#         for idx, box in enumerate(results.boxes):
+#             class_id = int(box.cls[0])
+#             conf = float(box.conf[0])
+#             class_name = model.names[class_id]
+#             box_coords = box.xyxy[0].cpu().numpy()
             
-            pdf.cell(0, 10, f'Detection {idx+1}:', 0, 1)
-            pdf.cell(0, 10, f'  • Sign Type: {class_name}', 0, 1)
-            pdf.cell(0, 10, f'  • Confidence: {conf:.2%}', 0, 1)
-            pdf.cell(0, 10, f'  • Location: x1={box_coords[0]:.1f}, y1={box_coords[1]:.1f}, x2={box_coords[2]:.1f}, y2={box_coords[3]:.1f}', 0, 1)
-            pdf.ln(5)
-    else:
-        pdf.cell(0, 10, 'No traffic signs detected in this image.', 0, 1)
-    
-    # Clean up temporary files
-    try:
-        os.remove(orig_img_path)
-        os.remove(detected_img_path)
-    except:
-        pass
+#             pdf.cell(0, 10, f'Detection {idx+1}:', 0, 1)
+#             pdf.cell(0, 10, f'  • Sign Type: {class_name}', 0, 1)
+#             pdf.cell(0, 10, f'  • Confidence: {conf:.2%}', 0, 1)
+#             pdf.cell(0, 10, f'  • Location: x1={box_coords[0]:.1f}, y1={box_coords[1]:.1f}, x2={box_coords[2]:.1f}, y2={box_coords[3]:.1f}', 0, 1)
+#             pdf.ln(5)
+#     else:
+#         pdf.cell(0, 10, 'No traffic signs detected in this image.', 0, 1)
+    
+#     # Clean up temporary files
+#     try:
+#         os.remove(orig_img_path)
+#         os.remove(detected_img_path)
+#     except:
+#         pass
     
-    # Save to bytes
-    pdf_bytes = io.BytesIO()
-    pdf.output(pdf_bytes)
-    pdf_bytes.seek(0)
+#     # Save to bytes
+#     pdf_bytes = io.BytesIO()
+#     pdf.output(pdf_bytes)
+#     pdf_bytes.seek(0)
     
-    return pdf_bytes
+#     return pdf_bytes
 
-def main():
-    # Header
-    st.markdown("""
-        <div class="header-container">
-            <h1>🚦 Traffic Sign Detection System</h1>
-            <p>Upload an image to detect and analyze traffic signs</p>
-        </div>
-    """, unsafe_allow_html=True)
+# def main():
+#     # Header
+#     st.markdown("""
+#         <div class="header-container">
+#             <h1>🚦 Traffic Sign Detection System</h1>
+#             <p>Upload an image to detect and analyze traffic signs</p>
+#         </div>
+#     """, unsafe_allow_html=True)
     
-    # Sidebar
-    with st.sidebar:
-        st.header("📊 Analysis Settings")
-        # confidence_threshold = st.slider("Detection Confidence Threshold", 0.0, 1.0, 0.25, 0.05)
-        enable_analytics = st.checkbox("Enable Advanced Analytics", True)
+#     # Sidebar
+#     with st.sidebar:
+#         st.header("📊 Analysis Settings")
+#         # confidence_threshold = st.slider("Detection Confidence Threshold", 0.0, 1.0, 0.25, 0.05) = st.slider("Detection Confidence Threshold", 0.0, 1.0, 0.25, 0.05)
+
+#         confidence_threshold = st.slider("Detection Confidence Threshold", 0.0, 1.0, 0.25, 0.05)
+#         enable_analytics = st.checkbox("Enable Advanced Analytics", True)
     
-    # Main content
-    col1, col2 = st.columns([2, 1])
+#     # Main content
+#     col1, col2 = st.columns([2, 1])
     
-    with col1:
-        st.markdown("<div class='upload-box'>", unsafe_allow_html=True)
-        uploaded_file = st.file_uploader(
-            "Drop your traffic sign image here or click to upload",
-            type=['jpg', 'jpeg', 'png']
-        )
-        st.markdown("</div>", unsafe_allow_html=True)
+#     with col1:
+#         st.markdown("<div class='upload-box'>", unsafe_allow_html=True)
+#         uploaded_file = st.file_uploader(
+#             "Drop your traffic sign image here or click to upload",
+#             type=['jpg', 'jpeg', 'png']
+#         )
+#         st.markdown("</div>", unsafe_allow_html=True)
     
-    with col2:
-        st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
-        st.markdown("### 📈 System Statistics")
-        st.metric("Total Analyses", st.session_state.total_analyses)
-        st.markdown("</div>", unsafe_allow_html=True)
+#     with col2:
+#         st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
+#         st.markdown("### 📈 System Statistics")
+#         st.metric("Total Analyses", st.session_state.total_analyses)
+#         st.markdown("</div>", unsafe_allow_html=True)
     
-    if uploaded_file:
-        # Load and process image
-        image_bytes = uploaded_file.read()
-        image = cv2.imdecode(np.frombuffer(image_bytes, np.uint8), cv2.IMREAD_COLOR)
+#     if uploaded_file:
+#         # Load and process image
+#         image_bytes = uploaded_file.read()
+#         image = cv2.imdecode(np.frombuffer(image_bytes, np.uint8), cv2.IMREAD_COLOR)
         
-        col1, col2 = st.columns(2)
+#         col1, col2 = st.columns(2)
         
-        with col1:
-            st.markdown("### Original Image")
-            image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
-            st.image(image_rgb)
+#         with col1:
+#             st.markdown("### Original Image")
+#             image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+#             st.image(image_rgb)
         
-        if st.button("🔍 Analyze Image", key="analyze_button"):
-            st.session_state.total_analyses += 1
+#         if st.button("🔍 Analyze Image", key="analyze_button"):
+#             st.session_state.total_analyses += 1
             
-            with st.spinner("Processing image..."):
-                # Load model if not already loaded
-                if st.session_state.model is None:
-                    st.session_state.model = load_model()
+#             with st.spinner("Processing image..."):
+#                 # Load model if not already loaded
+#                 if st.session_state.model is None:
+#                     st.session_state.model = load_model()
                 
-                if st.session_state.model is not None:
-                    # Progress bar
-                    progress_text = "Running analysis..."
-                    progress_bar = st.progress(0)
-                    # for i in range(100):
-                    #     progress_bar.progress(i + 1)
-                    #     if i == 30:
-                    #         progress_text = "Detecting signs..."
-                    #     elif i == 60:
-                    #         progress_text = "Analyzing patterns..."
-                    #     elif i == 90:
-                    #         progress_text = "Preparing results..."
-                    #     st.write(progress_text)
+#                 if st.session_state.model is not None:
+#                     # Progress bar
+#                     progress_text = "Running analysis..."
+#                     progress_bar = st.progress(0)
+#                     # for i in range(100):
+#                     #     progress_bar.progress(i + 1)
+#                     #     if i == 30:
+#                     #         progress_text = "Detecting signs..."
+#                     #     elif i == 60:
+#                     #         progress_text = "Analyzing patterns..."
+#                     #     elif i == 90:
+#                     #         progress_text = "Preparing results..."
+#                     #     st.write(progress_text)
                     
-                    # Run inference
-                    results = st.session_state.model.predict(source=image, conf=confidence_threshold)[0]
+#                     # Run inference
+#                     results = st.session_state.model.predict(source=image, conf=confidence_threshold)[0]
                     
-                    with col2:
-                        st.markdown("### Detection Results")
-                        plotted_image = results.plot()
-                        plotted_image_rgb = cv2.cvtColor(plotted_image, cv2.COLOR_BGR2RGB)
-                        st.image(plotted_image_rgb)
+#                     with col2:
+#                         st.markdown("### Detection Results")
+#                         plotted_image = results.plot()
+#                         plotted_image_rgb = cv2.cvtColor(plotted_image, cv2.COLOR_BGR2RGB)
+#                         st.image(plotted_image_rgb)
                     
-                    # Display detections and analytics
-                    if len(results.boxes) > 0:
-                        st.markdown("<div class='detection-box'>", unsafe_allow_html=True)
-                        st.markdown("### 🎯 Detection Details")
+#                     # Display detections and analytics
+#                     if len(results.boxes) > 0:
+#                         st.markdown("<div class='detection-box'>", unsafe_allow_html=True)
+#                         st.markdown("### 🎯 Detection Details")
                         
-                        for idx, box in enumerate(results.boxes):
-                            class_id = int(box.cls[0])
-                            conf = float(box.conf[0])
-                            class_name = st.session_state.model.names[class_id]
+#                         for idx, box in enumerate(results.boxes):
+#                             class_id = int(box.cls[0])
+#                             conf = float(box.conf[0])
+#                             class_name = st.session_state.model.names[class_id]
                             
-                            with st.expander(f"Detection {idx+1}: {class_name} ({conf:.2%})"):
-                                st.markdown(create_confidence_bar(conf), unsafe_allow_html=True)
-                                box_coords = box.xyxy[0].cpu().numpy()
-                                st.markdown(f"**Location:** x1={box_coords[0]:.1f}, y1={box_coords[1]:.1f}, x2={box_coords[2]:.1f}, y2={box_coords[3]:.1f}")
+#                             with st.expander(f"Detection {idx+1}: {class_name} ({conf:.2%})"):
+#                                 st.markdown(create_confidence_bar(conf), unsafe_allow_html=True)
+#                                 box_coords = box.xyxy[0].cpu().numpy()
+#                                 st.markdown(f"**Location:** x1={box_coords[0]:.1f}, y1={box_coords[1]:.1f}, x2={box_coords[2]:.1f}, y2={box_coords[3]:.1f}")
                         
-                        if enable_analytics:
-                            st.markdown("### 📊 Analytics")
-                            fig_conf, fig_class = create_visualization(results, st.session_state.model)
-                            if fig_conf and fig_class:
-                                col1, col2 = st.columns(2)
-                                with col1:
-                                    st.plotly_chart(fig_conf, use_container_width=True)
-                                with col2:
-                                    st.plotly_chart(fig_class, use_container_width=True)
+#                         if enable_analytics:
+#                             st.markdown("### 📊 Analytics")
+#                             fig_conf, fig_class = create_visualization(results, st.session_state.model)
+#                             if fig_conf and fig_class:
+#                                 col1, col2 = st.columns(2)
+#                                 with col1:
+#                                     st.plotly_chart(fig_conf, use_container_width=True)
+#                                 with col2:
+#                                     st.plotly_chart(fig_class, use_container_width=True)
                         
-                        # Summary metrics
-                        col1, col2, col3 = st.columns(3)
-                        with col1:
-                            st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
-                            st.metric("Total Detections", len(results.boxes))
-                            st.markdown("</div>", unsafe_allow_html=True)
-                        with col2:
-                            st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
-                            # avg_conf = float(torch.mean(results.boxes
-                            avg_conf = float(torch.mean(results.boxes.conf).item())
-                            st.metric("Average Confidence", f"{avg_conf:.1%}")
-                            st.markdown("</div>", unsafe_allow_html=True)
-                        with col3:
-                            st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
-                            unique_classes = len(set(results.boxes.cls.cpu().numpy()))
-                            st.metric("Unique Sign Types", unique_classes)
-                            st.markdown("</div>", unsafe_allow_html=True)
+#                         # Summary metrics
+#                         col1, col2, col3 = st.columns(3)
+#                         with col1:
+#                             st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
+#                             st.metric("Total Detections", len(results.boxes))
+#                             st.markdown("</div>", unsafe_allow_html=True)
+#                         with col2:
+#                             st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
+#                             # avg_conf = float(torch.mean(results.boxes
+#                             avg_conf = float(torch.mean(results.boxes.conf).item())
+#                             st.metric("Average Confidence", f"{avg_conf:.1%}")
+#                             st.markdown("</div>", unsafe_allow_html=True)
+#                         with col3:
+#                             st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
+#                             unique_classes = len(set(results.boxes.cls.cpu().numpy()))
+#                             st.metric("Unique Sign Types", unique_classes)
+#                             st.markdown("</div>", unsafe_allow_html=True)
                         
-                        # Generate and offer PDF report download
-                        st.markdown("### 📄 Download Report")
-                        pdf_bytes = generate_pdf_report(
-                            image,
-                            plotted_image,
-                            results,
-                            st.session_state.model,
-                            analytics_enabled=enable_analytics
-                        )
+#                         # Generate and offer PDF report download
+#                         st.markdown("### 📄 Download Report")
+#                         pdf_bytes = generate_pdf_report(
+#                             image,
+#                             plotted_image,
+#                             results,
+#                             st.session_state.model,
+#                             analytics_enabled=enable_analytics
+#                         )
                         
-                        # Create download button with custom styling
-                        st.markdown("""
-                            <style>
-                            .download-button {
-                                background: linear-gradient(45deg, #2ecc71, #27ae60);
-                                color: white;
-                                padding: 12px 24px;
-                                border-radius: 8px;
-                                border: none;
-                                cursor: pointer;
-                                transition: all 0.3s ease;
-                                text-decoration: none;
-                                display: inline-block;
-                                margin: 10px 0;
-                            }
-                            .download-button:hover {
-                                transform: translateY(-2px);
-                                box-shadow: 0 5px 15px rgba(0,0,0,0.2);
-                            }
-                            </style>
-                        """, unsafe_allow_html=True)
+#                         # Create download button with custom styling
+#                         st.markdown("""
+#                             <style>
+#                             .download-button {
+#                                 background: linear-gradient(45deg, #2ecc71, #27ae60);
+#                                 color: white;
+#                                 padding: 12px 24px;
+#                                 border-radius: 8px;
+#                                 border: none;
+#                                 cursor: pointer;
+#                                 transition: all 0.3s ease;
+#                                 text-decoration: none;
+#                                 display: inline-block;
+#                                 margin: 10px 0;
+#                             }
+#                             .download-button:hover {
+#                                 transform: translateY(-2px);
+#                                 box-shadow: 0 5px 15px rgba(0,0,0,0.2);
+#                             }
+#                             </style>
+#                         """, unsafe_allow_html=True)
                         
-                        # Convert PDF bytes to base64 for download
-                        b64_pdf = base64.b64encode(pdf_bytes.getvalue()).decode()
-                        href = f'<a href="data:application/pdf;base64,{b64_pdf}" download="traffic_sign_report.pdf" class="download-button">📥 Download Detection Report</a>'
-                        st.markdown(href, unsafe_allow_html=True)
+#                         # Convert PDF bytes to base64 for download
+#                         b64_pdf = base64.b64encode(pdf_bytes.getvalue()).decode()
+#                         href = f'<a href="data:application/pdf;base64,{b64_pdf}" download="traffic_sign_report.pdf" class="download-button">📥 Download Detection Report</a>'
+#                         st.markdown(href, unsafe_allow_html=True)
                         
-                        st.markdown("</div>", unsafe_allow_html=True)
-                    else:
-                        st.warning("No traffic signs detected in the image.")
-                else:
-                    st.error("Failed to load the model. Please check if the model file exists and try again.")
+#                         st.markdown("</div>", unsafe_allow_html=True)
+#                     else:
+#                         st.warning("No traffic signs detected in the image.")
+#                 else:
+#                     st.error("Failed to load the model. Please check if the model file exists and try again.")
 
 
-if __name__ == "__main__":
-    try:
-        main()
-    except Exception as e:
-        st.error(f"An error occurred: {str(e)}")
-        st.error("Please refresh the page and try again.")                           
+# if __name__ == "__main__":
+#     try:
+#         main()
+#     except Exception as e:
+#         st.error(f"An error occurred: {str(e)}")
+#         st.error("Please refresh the page and try again.")                           
 
 
 
@@ -421,310 +423,310 @@ if __name__ == "__main__":
 
 
 
-# import streamlit as st
-# from PIL import Image
-# import torch
-# import cv2
-# import numpy as np
-# from datetime import datetime
-# import plotly.express as px
-# import plotly.graph_objects as go
-# import pandas as pd
-# from ultralytics import YOLO
-# import os
+import streamlit as st
+from PIL import Image
+import torch
+import cv2
+import numpy as np
+from datetime import datetime
+import plotly.express as px
+import plotly.graph_objects as go
+import pandas as pd
+from ultralytics import YOLO
+import os
 
-# # Page config
-# st.set_page_config(
-#     page_title="Traffic Sign Detection System",
-#     page_icon="🚦",
-#     layout="wide",
-#     initial_sidebar_state="expanded"
-# )
+# Page config
+st.set_page_config(
+    page_title="Traffic Sign Detection System",
+    page_icon="🚦",
+    layout="wide",
+    initial_sidebar_state="expanded"
+)
 
-# # Custom CSS with improved styling
-# st.markdown("""
-#     <style>
-#     .stApp {
-#         background: linear-gradient(135deg, #1a1a2e 0%, #16213e 100%);
-#         color: #e5e5e5;
-#     }
-#     .upload-box {
-#         border: 2px dashed #4a4a8a;
-#         border-radius: 15px;
-#         padding: 30px;
-#         text-align: center;
-#         background: rgba(255,255,255,0.05);
-#         backdrop-filter: blur(10px);
-#         transition: all 0.3s ease;
-#     }
-#     .upload-box:hover {
-#         border-color: #6a6aaa;
-#         background: rgba(255,255,255,0.08);
-#     }
-#     .detection-box {
-#         background: rgba(255,255,255,0.07);
-#         padding: 25px;
-#         border-radius: 15px;
-#         margin: 15px 0;
-#         box-shadow: 0 4px 15px rgba(0,0,0,0.2);
-#     }
-#     .metrics-card {
-#         background: rgba(255,255,255,0.1);
-#         padding: 20px;
-#         border-radius: 10px;
-#         margin: 10px 0;
-#         transition: transform 0.3s ease;
-#     }
-#     .metrics-card:hover {
-#         transform: translateY(-5px);
-#     }
-#     .confidence-meter {
-#         height: 20px;
-#         background: rgba(255,255,255,0.1);
-#         border-radius: 10px;
-#         overflow: hidden;
-#         box-shadow: inset 0 0 5px rgba(0,0,0,0.2);
-#     }
-#     .header-container {
-#         padding: 20px;
-#         background: rgba(255,255,255,0.05);
-#         border-radius: 15px;
-#         margin-bottom: 20px;
-#         text-align: center;
-#     }
-#     .stButton>button {
-#         background: linear-gradient(45deg, #3498db, #2980b9);
-#         color: white;
-#         border: none;
-#         padding: 10px 20px;
-#         border-radius: 8px;
-#         transition: all 0.3s ease;
-#     }
-#     .stButton>button:hover {
-#         transform: translateY(-2px);
-#         box-shadow: 0 5px 15px rgba(0,0,0,0.2);
-#     }
-#     </style>
-# """, unsafe_allow_html=True)
+# Custom CSS with improved styling
+st.markdown("""
+    <style>
+    .stApp {
+        background: linear-gradient(135deg, #1a1a2e 0%, #16213e 100%);
+        color: #e5e5e5;
+    }
+    .upload-box {
+        border: 2px dashed #4a4a8a;
+        border-radius: 15px;
+        padding: 30px;
+        text-align: center;
+        background: rgba(255,255,255,0.05);
+        backdrop-filter: blur(10px);
+        transition: all 0.3s ease;
+    }
+    .upload-box:hover {
+        border-color: #6a6aaa;
+        background: rgba(255,255,255,0.08);
+    }
+    .detection-box {
+        background: rgba(255,255,255,0.07);
+        padding: 25px;
+        border-radius: 15px;
+        margin: 15px 0;
+        box-shadow: 0 4px 15px rgba(0,0,0,0.2);
+    }
+    .metrics-card {
+        background: rgba(255,255,255,0.1);
+        padding: 20px;
+        border-radius: 10px;
+        margin: 10px 0;
+        transition: transform 0.3s ease;
+    }
+    .metrics-card:hover {
+        transform: translateY(-5px);
+    }
+    .confidence-meter {
+        height: 20px;
+        background: rgba(255,255,255,0.1);
+        border-radius: 10px;
+        overflow: hidden;
+        box-shadow: inset 0 0 5px rgba(0,0,0,0.2);
+    }
+    .header-container {
+        padding: 20px;
+        background: rgba(255,255,255,0.05);
+        border-radius: 15px;
+        margin-bottom: 20px;
+        text-align: center;
+    }
+    .stButton>button {
+        background: linear-gradient(45deg, #3498db, #2980b9);
+        color: white;
+        border: none;
+        padding: 10px 20px;
+        border-radius: 8px;
+        transition: all 0.3s ease;
+    }
+    .stButton>button:hover {
+        transform: translateY(-2px);
+        box-shadow: 0 5px 15px rgba(0,0,0,0.2);
+    }
+    </style>
+""", unsafe_allow_html=True)
 
-# # Initialize session state
-# if 'model' not in st.session_state:
-#     st.session_state.model = None
-#     st.session_state.total_analyses = 0
+# Initialize session state
+if 'model' not in st.session_state:
+    st.session_state.model = None
+    st.session_state.total_analyses = 0
 
-# @st.cache_resource
-# def load_model():
-#     """Load and cache the YOLO model"""
-#     try:
-#         model = YOLO('best.pt')
-#         return model
-#     except Exception as e:
-#         st.error(f"Error loading model: {str(e)}")
-#         return None
+@st.cache_resource
+def load_model():
+    """Load and cache the YOLO model"""
+    try:
+        model = YOLO('best.pt')
+        return model
+    except Exception as e:
+        st.error(f"Error loading model: {str(e)}")
+        return None
 
-# def create_confidence_bar(confidence):
-#     """Create a visual confidence meter"""
-#     colors = {
-#         "high": "#00ff00",
-#         "medium": "#ffaa00",
-#         "low": "#ff0000"
-#     }
-#     color = colors["high"] if confidence > 0.7 else colors["medium"] if confidence > 0.5 else colors["low"]
-#     return f"""
-#         <div class="confidence-meter">
-#             <div style="width:{confidence*100}%; height:100%; background:{color}; 
-#                  transition:width 0.5s; text-align:center; color:white; line-height:20px;">
-#                 {confidence:.1%}
-#             </div>
-#         </div>
-#     """
+def create_confidence_bar(confidence):
+    """Create a visual confidence meter"""
+    colors = {
+        "high": "#00ff00",
+        "medium": "#ffaa00",
+        "low": "#ff0000"
+    }
+    color = colors["high"] if confidence > 0.7 else colors["medium"] if confidence > 0.5 else colors["low"]
+    return f"""
+        <div class="confidence-meter">
+            <div style="width:{confidence*100}%; height:100%; background:{color}; 
+                 transition:width 0.5s; text-align:center; color:white; line-height:20px;">
+                {confidence:.1%}
+            </div>
+        </div>
+    """
 
-# def create_visualization(results, model):
-#     """Create visualization plots for detection results"""
-#     if len(results.boxes) > 0:
-#         # Prepare data for visualization
-#         confidences = results.boxes.conf.cpu().numpy()
-#         classes = [model.names[int(cls)] for cls in results.boxes.cls.cpu().numpy()]
+def create_visualization(results, model):
+    """Create visualization plots for detection results"""
+    if len(results.boxes) > 0:
+        # Prepare data for visualization
+        confidences = results.boxes.conf.cpu().numpy()
+        classes = [model.names[int(cls)] for cls in results.boxes.cls.cpu().numpy()]
         
-#         # Create confidence distribution plot
-#         fig_conf = go.Figure(data=[go.Histogram(x=confidences, nbinsx=20)])
-#         fig_conf.update_layout(
-#             title="Confidence Score Distribution",
-#             xaxis_title="Confidence Score",
-#             yaxis_title="Count",
-#             template="plotly_dark"
-#         )
+        # Create confidence distribution plot
+        fig_conf = go.Figure(data=[go.Histogram(x=confidences, nbinsx=20)])
+        fig_conf.update_layout(
+            title="Confidence Score Distribution",
+            xaxis_title="Confidence Score",
+            yaxis_title="Count",
+            template="plotly_dark"
+        )
         
-#         # Create class distribution plot
-#         class_counts = pd.Series(classes).value_counts()
-#         fig_class = px.pie(values=class_counts.values, names=class_counts.index,
-#                           title="Distribution of Detected Signs")
-#         fig_class.update_layout(template="plotly_dark")
+        # Create class distribution plot
+        class_counts = pd.Series(classes).value_counts()
+        fig_class = px.pie(values=class_counts.values, names=class_counts.index,
+                          title="Distribution of Detected Signs")
+        fig_class.update_layout(template="plotly_dark")
         
-#         return fig_conf, fig_class
-#     return None, None
+        return fig_conf, fig_class
+    return None, None
 
-# def main():
-#     # Header
-#     st.markdown("""
-#         <div class="header-container">
-#             <h1>🚦 Traffic Sign Detection System</h1>
-#             <p>Upload an image to detect and analyze traffic signs</p>
-#         </div>
-#     """, unsafe_allow_html=True)
+def main():
+    # Header
+    st.markdown("""
+        <div class="header-container">
+            <h1>🚦 Traffic Sign Detection System</h1>
+            <p>Upload an image to detect and analyze traffic signs</p>
+        </div>
+    """, unsafe_allow_html=True)
     
-#     # Sidebar
-#     with st.sidebar:
-#         st.header("📊 Analysis Settings")
-#         confidence_threshold = st.slider("Detection Confidence Threshold", 0.0, 1.0, 0.25, 0.05)
-#         enable_analytics = st.checkbox("Enable Advanced Analytics", True)
+    # Sidebar
+    with st.sidebar:
+        st.header("📊 Analysis Settings")
+        confidence_threshold = st.slider("Detection Confidence Threshold", 0.0, 1.0, 0.25, 0.05)
+        enable_analytics = st.checkbox("Enable Advanced Analytics", True)
     
-#     # Main content
-#     col1, col2 = st.columns([2, 1])
+    # Main content
+    col1, col2 = st.columns([2, 1])
     
-#     with col1:
-#         st.markdown("<div class='upload-box'>", unsafe_allow_html=True)
-#         uploaded_file = st.file_uploader(
-#             "Drop your traffic sign image here or click to upload",
-#             type=['jpg', 'jpeg', 'png']
-#         )
-#         st.markdown("</div>", unsafe_allow_html=True)
+    with col1:
+        st.markdown("<div class='upload-box'>", unsafe_allow_html=True)
+        uploaded_file = st.file_uploader(
+            "Drop your traffic sign image here or click to upload",
+            type=['jpg', 'jpeg', 'png']
+        )
+        st.markdown("</div>", unsafe_allow_html=True)
     
-#     with col2:
-#         st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
-#         st.markdown("### 📈 System Statistics")
-#         st.metric("Total Analyses", st.session_state.total_analyses)
-#         st.markdown("</div>", unsafe_allow_html=True)
+    with col2:
+        st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
+        st.markdown("### 📈 System Statistics")
+        st.metric("Total Analyses", st.session_state.total_analyses)
+        st.markdown("</div>", unsafe_allow_html=True)
     
-#     if uploaded_file:
-#         # Load and process image
-#         image_bytes = uploaded_file.read()
-#         image = cv2.imdecode(np.frombuffer(image_bytes, np.uint8), cv2.IMREAD_COLOR)
+    if uploaded_file:
+        # Load and process image
+        image_bytes = uploaded_file.read()
+        image = cv2.imdecode(np.frombuffer(image_bytes, np.uint8), cv2.IMREAD_COLOR)
         
-#         col1, col2 = st.columns(2)
+        col1, col2 = st.columns(2)
         
-#         with col1:
-#             st.markdown("### Original Image")
-#             image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
-#             st.image(image_rgb)
+        with col1:
+            st.markdown("### Original Image")
+            image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+            st.image(image_rgb)
         
-#         if st.button("🔍 Analyze Image", key="analyze_button"):
-#             st.session_state.total_analyses += 1
+        if st.button("🔍 Analyze Image", key="analyze_button"):
+            st.session_state.total_analyses += 1
             
-#             with st.spinner("Processing image..."):
-#                 # Load model if not already loaded
-#                 if st.session_state.model is None:
-#                     st.session_state.model = load_model()
+            with st.spinner("Processing image..."):
+                # Load model if not already loaded
+                if st.session_state.model is None:
+                    st.session_state.model = load_model()
                 
-#                 if st.session_state.model is not None:
-#                     # Progress bar
-#                     progress_text = "Running analysis..."
-#                     progress_bar = st.progress(0)
-#                     # for i in range(100):
-#                     #     progress_bar.progress(i + 1)
-#                     #     if i == 30:
-#                     #         progress_text = "Detecting signs..."
-#                     #     elif i == 60:
-#                     #         progress_text = "Analyzing patterns..."
-#                     #     elif i == 90:
-#                     #         progress_text = "Preparing results..."
-#                     #     st.write(progress_text)
+                if st.session_state.model is not None:
+                    # Progress bar
+                    progress_text = "Running analysis..."
+                    progress_bar = st.progress(0)
+                    # for i in range(100):
+                    #     progress_bar.progress(i + 1)
+                    #     if i == 30:
+                    #         progress_text = "Detecting signs..."
+                    #     elif i == 60:
+                    #         progress_text = "Analyzing patterns..."
+                    #     elif i == 90:
+                    #         progress_text = "Preparing results..."
+                    #     st.write(progress_text)
                     
-#                     # Run inference
-#                     results = st.session_state.model.predict(source=image, conf=confidence_threshold)[0]
+                    # Run inference
+                    results = st.session_state.model.predict(source=image, conf=confidence_threshold)[0]
                     
-#                     with col2:
-#                         st.markdown("### Detection Results")
-#                         plotted_image = results.plot()
-#                         plotted_image_rgb = cv2.cvtColor(plotted_image, cv2.COLOR_BGR2RGB)
-#                         st.image(plotted_image_rgb)
+                    with col2:
+                        st.markdown("### Detection Results")
+                        plotted_image = results.plot()
+                        plotted_image_rgb = cv2.cvtColor(plotted_image, cv2.COLOR_BGR2RGB)
+                        st.image(plotted_image_rgb)
                     
-#                     # Display detections and analytics
-#                     if len(results.boxes) > 0:
-#                         st.markdown("<div class='detection-box'>", unsafe_allow_html=True)
-#                         st.markdown("### 🎯 Detection Details")
+                    # Display detections and analytics
+                    if len(results.boxes) > 0:
+                        st.markdown("<div class='detection-box'>", unsafe_allow_html=True)
+                        st.markdown("### 🎯 Detection Details")
                         
-#                         for idx, box in enumerate(results.boxes):
-#                             class_id = int(box.cls[0])
-#                             conf = float(box.conf[0])
-#                             class_name = st.session_state.model.names[class_id]
+                        for idx, box in enumerate(results.boxes):
+                            class_id = int(box.cls[0])
+                            conf = float(box.conf[0])
+                            class_name = st.session_state.model.names[class_id]
                             
-#                             with st.expander(f"Detection {idx+1}: {class_name} ({conf:.2%})"):
-#                                 st.markdown(create_confidence_bar(conf), unsafe_allow_html=True)
-#                                 box_coords = box.xyxy[0].cpu().numpy()
-#                                 st.markdown(f"**Location:** x1={box_coords[0]:.1f}, y1={box_coords[1]:.1f}, x2={box_coords[2]:.1f}, y2={box_coords[3]:.1f}")
+                            with st.expander(f"Detection {idx+1}: {class_name} ({conf:.2%})"):
+                                st.markdown(create_confidence_bar(conf), unsafe_allow_html=True)
+                                box_coords = box.xyxy[0].cpu().numpy()
+                                st.markdown(f"**Location:** x1={box_coords[0]:.1f}, y1={box_coords[1]:.1f}, x2={box_coords[2]:.1f}, y2={box_coords[3]:.1f}")
                         
-#                         if enable_analytics:
-#                             st.markdown("### 📊 Analytics")
-#                             fig_conf, fig_class = create_visualization(results, st.session_state.model)
-#                             if fig_conf and fig_class:
-#                                 col1, col2 = st.columns(2)
-#                                 with col1:
-#                                     st.plotly_chart(fig_conf, use_container_width=True)
-#                                 with col2:
-#                                     st.plotly_chart(fig_class, use_container_width=True)
+                        if enable_analytics:
+                            st.markdown("### 📊 Analytics")
+                            fig_conf, fig_class = create_visualization(results, st.session_state.model)
+                            if fig_conf and fig_class:
+                                col1, col2 = st.columns(2)
+                                with col1:
+                                    st.plotly_chart(fig_conf, use_container_width=True)
+                                with col2:
+                                    st.plotly_chart(fig_class, use_container_width=True)
                         
-#                         # Summary metrics
-#                         col1, col2, col3 = st.columns(3)
-#                         with col1:
-#                             st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
-#                             st.metric("Total Detections", len(results.boxes))
-#                             st.markdown("</div>", unsafe_allow_html=True)
-#                         with col2:
-#                             st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
-#                             avg_conf = float(torch.mean(results.boxes.conf).item())
-#                             st.metric("Average Confidence", f"{avg_conf:.2%}")
-#                             st.markdown("</div>", unsafe_allow_html=True)
-#                         with col3:
-#                             st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
-#                             unique_classes = len(set(results.boxes.cls.cpu().numpy()))
-#                             st.metric("Unique Sign Types", unique_classes)
-#                             st.markdown("</div>", unsafe_allow_html=True)
+                        # Summary metrics
+                        col1, col2, col3 = st.columns(3)
+                        with col1:
+                            st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
+                            st.metric("Total Detections", len(results.boxes))
+                            st.markdown("</div>", unsafe_allow_html=True)
+                        with col2:
+                            st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
+                            avg_conf = float(torch.mean(results.boxes.conf).item())
+                            st.metric("Average Confidence", f"{avg_conf:.2%}")
+                            st.markdown("</div>", unsafe_allow_html=True)
+                        with col3:
+                            st.markdown("<div class='metrics-card'>", unsafe_allow_html=True)
+                            unique_classes = len(set(results.boxes.cls.cpu().numpy()))
+                            st.metric("Unique Sign Types", unique_classes)
+                            st.markdown("</div>", unsafe_allow_html=True)
                         
-#                     else:
-#                         st.warning("No traffic signs detected in this image.")
-    
-#     # Footer
-#     st.markdown("---")
-#     st.markdown(
-#         """
-#         <div style='text-align: center'>
-#             <p>Traffic Sign Detection System | Built with Streamlit and YOLOv8</p>
-#             <p>Deployed on Hugging Face Spaces | 2024</p>
-#         </div>
-#         """, 
-#         unsafe_allow_html=True
-#     )
+                    else:
+                        st.warning("No traffic signs detected in this image.")
+    
+    # Footer
+    st.markdown("---")
+    st.markdown(
+        """
+        <div style='text-align: center'>
+            <p>Traffic Sign Detection System | Built with Streamlit and YOLOv8</p>
+            <p>Deployed on Hugging Face Spaces | 2024</p>
+        </div>
+        """, 
+        unsafe_allow_html=True
+    )
 
-#     # Help section in sidebar
-#     with st.sidebar:
-#         st.markdown("---")
-#         with st.expander("ℹ️ Help & Instructions"):
-#             st.markdown("""
-#             ### How to Use:
-#             1. Upload an image containing traffic signs
-#             2. Adjust the confidence threshold if needed
-#             3. Click 'Analyze Image' to start detection
-#             4. View results and analytics
+    # Help section in sidebar
+    with st.sidebar:
+        st.markdown("---")
+        with st.expander("ℹ️ Help & Instructions"):
+            st.markdown("""
+            ### How to Use:
+            1. Upload an image containing traffic signs
+            2. Adjust the confidence threshold if needed
+            3. Click 'Analyze Image' to start detection
+            4. View results and analytics
             
-#             ### Features:
-#             - Real-time traffic sign detection
-#             - Advanced analytics visualization
-#             - Confidence score analysis
-#             - Multiple sign detection support
+            ### Features:
+            - Real-time traffic sign detection
+            - Advanced analytics visualization
+            - Confidence score analysis
+            - Multiple sign detection support
             
-#             ### Tips:
-#             - Use clear, well-lit images
-#             - Adjust confidence threshold for better results
-#             - Enable analytics for detailed insights
-#             """)
+            ### Tips:
+            - Use clear, well-lit images
+            - Adjust confidence threshold for better results
+            - Enable analytics for detailed insights
+            """)
 
-# if __name__ == "__main__":
-#     try:
-#         main()
-#     except Exception as e:
-#         st.error(f"An error occurred: {str(e)}")
-#         st.error("Please refresh the page and try again.")
+if __name__ == "__main__":
+    try:
+        main()
+    except Exception as e:
+        st.error(f"An error occurred: {str(e)}")
+        st.error("Please refresh the page and try again.")