the error which is being thrown WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. model.compile_metrics will be empty until you train or evaluate the model.
i tried chatgpt and google but didn’t find a solution
i saw a solution saying try dummy prediction so it’ll force the model to build metrics but i couldn’t figure it out
the code is as follows

import streamlit as st
import os
import numpy as np
from tensorflow.keras.preprocessing.image import ImageDataGenerator, img_to_array
from tensorflow.keras.models import Sequential, load_model
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Input
from tensorflow.keras import Model
from PIL import Image

# Define paths to training and testing data
train_data_path = 'C:\Users\kiree\OneDrive\Desktop\engineering\underwater-image-enhancement-main\underwater-image-enhancement-main\abc'
test_data_path = 'C:\Users\kiree\OneDrive\Desktop\engineering\underwater-image-enhancement-main\underwater-image-enhancement-main\abd'

# Function to build and train the CNN model
def train_model():
    st.write("Training the model...")
    # Set parameters
    image_height, image_width = 200, 200
    num_channels = 3
    input_size = (image_height, image_width, num_channels)
    batch_size = 32
    num_epochs = 50

    # Create data generators for training and validation data
    train_datagen = ImageDataGenerator(rescale=1./255, validation_split=0.3)

    train_generator = train_datagen.flow_from_directory(
        train_data_path,
        target_size=(image_height, image_width),
        batch_size=batch_size,
        class_mode='categorical',
        subset='training')

    validation_generator = train_datagen.flow_from_directory(
        train_data_path,
        target_size=(image_height, image_width),
        batch_size=batch_size,
        class_mode='categorical',
        subset='validation')

    # Build the CNN model
    inputs = Input(shape=input_size)
    x = Conv2D(8, (3, 3), padding='same', activation='relu')(inputs)
    x = MaxPooling2D(pool_size=(2, 2))(x)
    x = Conv2D(16, (3, 3), padding='same', activation='relu')(x)
    x = MaxPooling2D(pool_size=(2, 2))(x)
    x = Conv2D(32, (2, 2), padding='same', activation='relu')(x)
    x = MaxPooling2D(pool_size=(2, 2))(x)
    x = Conv2D(64, (3, 3), padding='same', activation='relu')(x)
    x = MaxPooling2D(pool_size=(2, 2))(x)
    x = Conv2D(128, (3, 3), padding='same', activation='relu')(x)
    x = MaxPooling2D(pool_size=(2, 2))(x)
    x = Flatten()(x)
    outputs = Dense(4, activation='softmax')(x)

    model = Model(inputs=inputs, outputs=outputs)

    # Compile the model
    model.compile(optimizer='sgd', loss='categorical_crossentropy', metrics=['accuracy'])

    # Train the model
    model.fit(
        train_generator,
        steps_per_epoch=train_generator.samples // batch_size,
        epochs=num_epochs,
        validation_data=validation_generator,
        validation_steps=validation_generator.samples // batch_size)

    # Save the trained model
    model.save('trained_model.h5')
    st.write("Model trained and saved successfully!")

# Function to load and test the model on a single image
@st.cache_resource
def load_trained_model():
    model_path = 'trained_model.h5'
    if os.path.exists(model_path):
        model = load_model(model_path)
        model.compile(optimizer='sgd', loss='categorical_crossentropy', metrics=['accuracy'])
        
        # Perform a dummy prediction to build metrics
        dummy_data = np.random.random((1, 200, 200, 3)).astype(np.float32)
        model.predict(dummy_data)
        
        return model
    return None

def test_model(model):
    st.write("Testing the model...")

    # Allow user to select an image for testing
    st.write("Select an image for testing:")
    uploaded_file = st.file_uploader("Upload an image...", type=["jpg", "jpeg", "png"])
    if uploaded_file is not None:
        image = Image.open(uploaded_file)
        st.image(image, caption='Uploaded Image', use_column_width=True)

        # Load and preprocess the test image
        image = image.resize((200, 200))  # Resize using PIL
        image = img_to_array(image) / 255.0
        image = np.expand_dims(image, axis=0)

        # Predict the class probabilities
        class_names = ['class_1', 'class_2', 'class_3', 'class_4']
        probabilities = model.predict(image)[0]

        # Display the predicted class and probability
        for i in range(len(class_names)):
            st.write(f"{class_names[i]}: {probabilities[i]*100:.2f}%")

# Streamlit GUI
st.title("CNN Model Training and Testing")

# Buttons for training and testing
train_button = st.button("Train Model")
test_button = st.button("Test Model")

# Perform actions based on button clicks
if train_button:
    train_model()

if test_button:
    model = load_trained_model()
    if model:
        test_model(model)
    else:
        st.write("Model file does not exist.")