请给出一个用TensorFlow搭建的可用于三种图像类别分类识别的VGG16模型代码，优化器采用Adam，损失函数采用交叉熵损失函数

以下是一个用TensorFlow搭建的可用于三种图像类别分类识别的VGG16模型代码，优化器采用Adam，损失函数采用交叉熵损失函数：

import tensorflow as tf

def vgg16(num_classes):
    # input layer
    inputs = tf.keras.layers.Input(shape=(224, 224, 3))

    # convolution layers
    x = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(inputs)
    x = tf.keras.layers.Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
    x = tf.keras.layers.MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)

    x = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
    x = tf.keras.layers.Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
    x = tf.keras.layers.MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)

    x = tf.keras.layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
    x = tf.keras.layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
    x = tf.keras.layers.Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
    x = tf.keras.layers.MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)

    x = tf.keras.layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
    x = tf.keras.layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
    x = tf.keras.layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
    x = tf.keras.layers.MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)

    x = tf.keras.layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
    x = tf.keras.layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
    x = tf.keras.layers.Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)
    x = tf.keras.layers.MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)

    # fully connected layers
    x = tf.keras.layers.Flatten(name='flatten')(x)
    x = tf.keras.layers.Dense(4096, activation='relu', name='fc1')(x)
    x = tf.keras.layers.Dense(4096, activation='relu', name='fc2')(x)
    outputs = tf.keras.layers.Dense(num_classes, activation='softmax', name='predictions')(x)

    # create model
    model = tf.keras.models.Model(inputs=inputs, outputs=outputs, name='vgg16')

    # compile model
    optimizer = tf.keras.optimizers.Adam()
    loss_fn = tf.keras.losses.CategoricalCrossentropy()
    model.compile(optimizer=optimizer, loss=loss_fn, metrics=['accuracy'])

    return model