简单写一个VGG神经网络代码

好的，以下是一个简单的VGG神经网络代码，包含了VGG16和VGG19两个模型的实现：

import tensorflow as tf

def conv_block(inputs, num_filters, kernel_size, strides, padding):
    x = tf.keras.layers.Conv2D(num_filters, kernel_size, strides=strides, padding=padding)(inputs)
    x = tf.keras.layers.BatchNormalization()(x)
    x = tf.keras.layers.Activation('relu')(x)
    return x

def vgg16(input_shape=(224, 224, 3), num_classes=1000):
    inputs = tf.keras.layers.Input(shape=input_shape)

    x = conv_block(inputs, 64, 3, 1, 'same')
    x = conv_block(x, 64, 3, 1, 'same')
    x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)

    x = conv_block(x, 128, 3, 1, 'same')
    x = conv_block(x, 128, 3, 1, 'same')
    x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)

    x = conv_block(x, 256, 3, 1, 'same')
    x = conv_block(x, 256, 3, 1, 'same')
    x = conv_block(x, 256, 3, 1, 'same')
    x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)

    x = conv_block(x, 512, 3, 1, 'same')
    x = conv_block(x, 512, 3, 1, 'same')
    x = conv_block(x, 512, 3, 1, 'same')
    x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)

    x = conv_block(x, 512, 3, 1, 'same')
    x = conv_block(x, 512, 3, 1, 'same')
    x = conv_block(x, 512, 3, 1, 'same')
    x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)

    x = tf.keras.layers.Flatten()(x)
    x = tf.keras.layers.Dense(4096, activation='relu')(x)
    x = tf.keras.layers.Dropout(0.5)(x)
    x = tf.keras.layers.Dense(4096, activation='relu')(x)
    x = tf.keras.layers.Dropout(0.5)(x)
    outputs = tf.keras.layers.Dense(num_classes, activation='softmax')(x)

    model = tf.keras.models.Model(inputs, outputs)
    return model

def vgg19(input_shape=(224, 224, 3), num_classes=1000):
    inputs = tf.keras.layers.Input(shape=input_shape)

    x = conv_block(inputs, 64, 3, 1, 'same')
    x = conv_block(x, 64, 3, 1, 'same')
    x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)

    x = conv_block(x, 128, 3, 1, 'same')
    x = conv_block(x, 128, 3, 1, 'same')
    x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)

    x = conv_block(x, 256, 3, 1, 'same')
    x = conv_block(x, 256, 3, 1, 'same')
    x = conv_block(x, 256, 3, 1, 'same')
    x = conv_block(x, 256, 3, 1, 'same')
    x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)

    x = conv_block(x, 512, 3, 1, 'same')
    x = conv_block(x, 512, 3, 1, 'same')
    x = conv_block(x, 512, 3, 1, 'same')
    x = conv_block(x, 512, 3, 1, 'same')
    x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)

    x = conv_block(x, 512, 3, 1, 'same')
    x = conv_block(x, 512, 3, 1, 'same')
    x = conv_block(x, 512, 3, 1, 'same')
    x = conv_block(x, 512, 3, 1, 'same')
    x = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(x)

    x = tf.keras.layers.Flatten()(x)
    x = tf.keras.layers.Dense(4096, activation='relu')(x)
    x = tf.keras.layers.Dropout(0.5)(x)
    x = tf.keras.layers.Dense(4096, activation='relu')(x)
    x = tf.keras.layers.Dropout(0.5)(x)
    outputs = tf.keras.layers.Dense(num_classes, activation='softmax')(x)

    model = tf.keras.models.Model(inputs, outputs)
    return model

以上代码中，我们定义了一个名为conv_block的函数，用于构建卷积块。然后我们按照VGG16和VGG19的结构，依次堆叠卷积块和池化层，最后接上全连接层进行分类。

可以根据实际需要，调整输入图片的大小和分类的类别数量。