Create app.py

app.py

@@ -0,0 +1,232 @@
+import streamlit as st
+import tensorflow as tf
+import numpy as np
+from PIL import Image
+import json
+import os
+
+# Page configuration
+st.set_page_config(
+    page_title="Indian Food Classifier",
+    page_icon="🍛",
+    layout="wide",
+    initial_sidebar_state="expanded"
+)
+
+# Custom CSS for better UI
+st.markdown("""
+    <style>
+    .stApp {
+        background-color: #f5f5f5;
+    }
+    .main-header {
+        text-align: center;
+        padding: 2rem;
+        background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+        color: white;
+        border-radius: 10px;
+        margin-bottom: 2rem;
+    }
+    .prediction-card {
+        background-color: white;
+        padding: 1.5rem;
+        border-radius: 10px;
+        box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+        margin: 1rem 0;
+    }
+    .top1 {
+        background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+        color: white;
+        padding: 1rem;
+        border-radius: 10px;
+        margin: 0.5rem 0;
+    }
+    .top2 {
+        background-color: #e3f2fd;
+        padding: 0.8rem;
+        border-radius: 8px;
+        margin: 0.5rem 0;
+    }
+    .top3 {
+        background-color: #f3e5f5;
+        padding: 0.8rem;
+        border-radius: 8px;
+        margin: 0.5rem 0;
+    }
+    </style>
+""", unsafe_allow_html=True)
+
+# Load model and class names
+@st.cache_resource
+def load_model():
+    """Load the trained model"""
+    try:
+        model = tf.keras.models.load_model('dish_classifier_final.keras')
+        return model
+    except:
+        st.error("Model file not found! Please upload your model file.")
+        return None
+
+@st.cache_data
+def load_class_names():
+    """Load class names"""
+    try:
+        with open('class_names.json', 'r') as f:
+            class_names = json.load(f)
+        return class_names
+    except:
+        st.error("Class names file not found!")
+        return None
+
+def preprocess_image(image):
+    """Preprocess image for model prediction"""
+    # Resize to 224x224
+    image = image.resize((224, 224))
+    
+    # Convert to array
+    img_array = np.array(image)
+    
+    # Normalize (EfficientNetV2 preprocessing)
+    img_array = img_array / 255.0
+    
+    # Expand dimensions
+    img_array = np.expand_dims(img_array, axis=0)
+    
+    return img_array
+
+def predict_image(model, class_names, image):
+    """Make prediction"""
+    processed_image = preprocess_image(image)
+    predictions = model.predict(processed_image, verbose=0)[0]
+    
+    # Get top 5 predictions
+    top_5_idx = np.argsort(predictions)[-5:][::-1]
+    top_5_labels = [class_names[idx] for idx in top_5_idx]
+    top_5_probs = [predictions[idx] * 100 for idx in top_5_idx]
+    
+    return top_5_idx, top_5_labels, top_5_probs
+
+def main():
+    # Header
+    st.markdown("""
+    <div class="main-header">
+        <h1>🍛 Indian Food Classifier</h1>
+        <p>Upload a photo of Indian food and AI will identify it!</p>
+        <p style="font-size: 0.9rem; opacity: 0.9;">Supports 80+ Indian dishes with 85% Top-5 Accuracy</p>
+    </div>
+    """, unsafe_allow_html=True)
+    
+    # Sidebar
+    with st.sidebar:
+        st.markdown("### 📊 Model Information")
+        st.info("""
+        - **Model:** EfficientNetV2S
+        - **Classes:** 80 Indian Dishes
+        - **Accuracy:** 56.25%
+        - **Top-3 Accuracy:** 77.38%
+        - **Top-5 Accuracy:** 84.62%
+        """)
+        
+        st.markdown("### 🍽️ Supported Dishes (Sample)")
+        st.markdown("""
+        - Butter Chicken
+        - Biryani (Various types)
+        - Dal Makhani
+        - Naan
+        - Samosa
+        - Gulab Jamun
+        - And 73 more...
+        """)
+        
+        st.markdown("### 📝 How to Use")
+        st.markdown("""
+        1. Click 'Browse files' below
+        2. Upload an image of Indian food
+        3. Wait for AI prediction
+        4. See top 5 predictions with confidence scores
+        """)
+        
+        st.markdown("---")
+        st.markdown("Made with ❤️ using TensorFlow & Streamlit")
+    
+    # Main content
+    col1, col2 = st.columns([1, 1])
+    
+    with col1:
+        st.markdown("### 📤 Upload Image")
+        uploaded_file = st.file_uploader(
+            "Choose an image...",
+            type=['jpg', 'jpeg', 'png', 'webp'],
+            help="Upload a clear image of Indian food for best results"
+        )
+        
+        if uploaded_file is not None:
+            image = Image.open(uploaded_file)
+            st.image(image, caption='Uploaded Image', use_container_width=True)
+    
+    with col2:
+        if uploaded_file is not None:
+            st.markdown("### 🔍 Prediction Results")
+            
+            with st.spinner('Analyzing your food image...'):
+                # Load model and class names
+                model = load_model()
+                class_names = load_class_names()
+                
+                if model is not None and class_names is not None:
+                    # Make prediction
+                    top_5_idx, top_5_labels, top_5_probs = predict_image(model, class_names, image)
+                    
+                    # Display results
+                    st.markdown('<div class="prediction-card">', unsafe_allow_html=True)
+                    
+                    # Top 1 prediction
+                    st.markdown(f"""
+                    <div class="top1">
+                        <h3>🥇 Top Prediction</h3>
+                        <h2>{top_5_labels[0]}</h2>
+                        <p>Confidence: {top_5_probs[0]:.2f}%</p>
+                    </div>
+                    """, unsafe_allow_html=True)
+                    
+                    # Top 2 prediction
+                    st.markdown(f"""
+                    <div class="top2">
+                        <strong>🥈 Second:</strong> {top_5_labels[1]} <br>
+                        <span style="color: #666;">Confidence: {top_5_probs[1]:.2f}%</span>
+                    </div>
+                    """, unsafe_allow_html=True)
+                    
+                    # Top 3 prediction
+                    st.markdown(f"""
+                    <div class="top3">
+                        <strong>🥉 Third:</strong> {top_5_labels[2]} <br>
+                        <span style="color: #666;">Confidence: {top_5_probs[2]:.2f}%</span>
+                    </div>
+                    """, unsafe_allow_html=True)
+                    
+                    # Top 4 & 5
+                    st.markdown(f"""
+                    <div style="margin-top: 1rem;">
+                        <p><strong>4th:</strong> {top_5_labels[3]} ({top_5_probs[3]:.2f}%)</p>
+                        <p><strong>5th:</strong> {top_5_labels[4]} ({top_5_probs[4]:.2f}%)</p>
+                    </div>
+                    """, unsafe_allow_html=True)
+                    
+                    st.markdown('</div>', unsafe_allow_html=True)
+                    
+                    # Add confidence meter
+                    st.markdown("### 📊 Confidence Meter")
+                    st.progress(top_5_probs[0] / 100)
+    
+    # Footer
+    st.markdown("---")
+    st.markdown("""
+    <div style="text-align: center; color: #666; font-size: 0.8rem;">
+        <p>⚠️ Note: Model accuracy is 56% for exact match, 85% for Top-5 predictions.<br>
+        For best results, use clear, well-lit images of single dishes.</p>
+    </div>
+    """, unsafe_allow_html=True)
+
+if __name__ == "__main__":
+    main()