VGG16网络代码实现

以下是VGG16网络的代码实现：

import tensorflow as tf

def VGG16(input_shape=(224, 224, 3), num_classes=1000):
    model = tf.keras.Sequential([
        # Block 1
        tf.keras.layers.Conv2D(64, (3, 3), activation='relu', padding='same', input_shape=input_shape),
        tf.keras.layers.Conv2D(64, (3, 3), activation='relu', padding='same'),
        tf.keras.layers.MaxPooling2D((2, 2), strides=(2, 2)),

        # Block 2
        tf.keras.layers.Conv2D(128, (3, 3), activation='relu', padding='same'),
        tf.keras.layers.Conv2D(128, (3, 3), activation='relu', padding='same'),
        tf.keras.layers.MaxPooling2D((2, 2), strides=(2, 2)),

        # Block 3
        tf.keras.layers.Conv2D(256, (3, 3), activation='relu', padding='same'),
        tf.keras.layers.Conv2D(256, (3, 3), activation='relu', padding='same'),
        tf.keras.layers.Conv2D(256, (3, 3), activation='relu', padding='same'),
        tf.keras.layers.MaxPooling2D((2, 2), strides=(2, 2)),

        # Block 4
        tf.keras.layers.Conv2D(512, (3, 3), activation='relu', padding='same'),
        tf.keras.layers.Conv2D(512, (3, 3), activation='relu', padding='same'),
        tf.keras.layers.Conv2D(512, (3, 3), activation='relu', padding='same'),
        tf.keras.layers.MaxPooling2D((2, 2), strides=(2, 2)),

        # Block 5
        tf.keras.layers.Conv2D(512, (3, 3), activation='relu', padding='same'),
        tf.keras.layers.Conv2D(512, (3, 3), activation='relu', padding='same'),
        tf.keras.layers.Conv2D(512, (3, 3), activation='relu', padding='same'),
        tf.keras.layers.MaxPooling2D((2, 2), strides=(2, 2)),

        # Classifier
        tf.keras.layers.Flatten(),
        tf.keras.layers.Dense(4096, activation='relu'),
        tf.keras.layers.Dropout(0.5),
        tf.keras.layers.Dense(4096, activation='relu'),
        tf.keras.layers.Dropout(0.5),
        tf.keras.layers.Dense(num_classes, activation='softmax')
    ])
    
    return model

这个实现使用了 TensorFlow 2.x 的 Keras 接口，并且模型中的每个卷积层都使用了相同的参数设置，即卷积核大小为 3x3，使用 ReLU 激活函数，padding 方式为 same。在模型的最后使用了全连接层，其中第一个全连接层的节点数为 4096，第二个全连接层的节点数也为 4096，最终输出层使用 softmax 激活函数。