# app.py
import streamlit as st
import tensorflow as tf
from tensorflow import keras
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split

# Load CIFAR-10 dataset
(x_train, y_train), (x_test, y_test) = keras.datasets.cifar10.load_data()

# Normalize pixel values to [0, 1]
x_train, x_test = x_train / 255.0, x_test / 255.0

# Split training data into training and validation sets
x_train, x_val, y_train, y_val = train_test_split(x_train, y_train, test_size=0.2, random_state=42)

# Define a simple CNN model
def create_model():
    model = keras.models.Sequential([
        keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)),
        keras.layers.MaxPooling2D((2, 2)),
        keras.layers.Conv2D(64, (3, 3), activation='relu'),
        keras.layers.MaxPooling2D((2, 2)),
        keras.layers.Conv2D(128, (3, 3), activation='relu'),
        keras.layers.Flatten(),
        keras.layers.Dense(128, activation='relu'),
        keras.layers.Dense(10, activation='softmax')
    ])
    return model

# Check if the model is already saved
import os
if not os.path.exists("cifar10_cnn_model.h5"):
    # Create and compile the model
    model = create_model()
    model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

    # Train the model
    st.write("Training the model...")
    history = model.fit(x_train, y_train, epochs=40, validation_data=(x_val, y_val))  # Reduced epochs for quick testing

    # Save the model
    model.save("cifar10_cnn_model.h5")
    st.write("Model saved as 'cifar10_cnn_model.h5'")
else:
    # Load the pre-trained model
    st.write("Loading pre-trained model...")
    model = keras.models.load_model("cifar10_cnn_model.h5")

# Class names for CIFAR-10 dataset
class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']

# Streamlit app title
st.title("Image Detection System")

# Upload image
uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])

if uploaded_file is not None:
    # Display the uploaded image
    image = Image.open(uploaded_file)
    st.image(image, caption="Uploaded Image", use_column_width=True)

    # Preprocess the image
    image = image.resize((32, 32))  # Resize to match CIFAR-10 input size
    image = np.array(image) / 255.0  # Normalize pixel values
    image = np.expand_dims(image, axis=0)  # Add batch dimension

    # Make prediction
    predictions = model.predict(image)
    predicted_class = np.argmax(predictions)
    confidence = np.max(predictions) * 100

    # Display results
    st.write(f"**Prediction:** {class_names[predicted_class]}")
    st.write(f"**Confidence:** {confidence:.2f}%")
model.save("cifar10_cnn_model.keras")