model.py

from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, Flatten, Dense
from tensorflow.keras.models import Model

def sign_cnn_model(input_shape, num_classes):
    """
    Creates a Convolutional Neural Network (CNN) model.

    Args:
        input_shape (tuple): The shape of the input data (height, width, channels).
        num_classes (int): The number of classes for the classification task.

    Returns:
        model (tensorflow.keras.Model): The constructed CNN model.
    """
    # Input layer
    input_layer = Input(shape=input_shape)

    # 1st Convolutional Layer
    x = Conv2D(32, (3, 3), activation='relu')(input_layer)
    x = MaxPooling2D(pool_size=(2, 2))(x)

    # 2nd Convolutional Layer
    x = Conv2D(64, (3, 3), activation='relu')(x)
    x = MaxPooling2D(pool_size=(2, 2))(x)

    x = Conv2D(64, (3, 3), activation='relu')(x)
    x = MaxPooling2D(pool_size=(2, 2))(x)

    # Flatten layer to convert 2D feature maps into 1D feature vectors
    x = Flatten()(x)

    # Fully Connected Dense Layer
    x = Dense(128, activation='relu')(x)

    # Output Layer with softmax activation for classification
    output_layer = Dense(num_classes, activation='softmax')(x)

    # Define the model
    model = Model(inputs=input_layer, outputs=output_layer)

    return model