• 🍨 本文为🔗365天深度学习训练营中的学习记录博客
• 🍖 原作者：K同学啊

import tensorflow as tf
import tensorflow.keras.layers as layers
from tensorflow.keras.models import Model

def block2(x, filters, kernel_size=3, stride=1, conv_shortcut=False, name=None):
    preact = layers.BatchNormalization(name=name + '_preact_bn')(x)
    preact = layers.Activation('relu', name=name + '_preact_relu')(preact)

    if conv_shortcut:
        shortcut = layers.Conv2D(4 * filters, 1, strides=stride, name=name + '_0_conv')(preact)
    else:
        shortcut = layers.MaxPooling2D(1, strides=stride)(x) if stride > 1 else x

    x = layers.Conv2D(filters, 1, strides=1, use_bias=False, name=name + '_1_conv')(preact)
    x = layers.BatchNormalization(name=name + '_1_bn')(x)
    x = layers.Activation('relu', name=name + '_1_relu')(x)

    x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name=name + '_2_pad')(x)
    x = layers.Conv2D(filters,
                      kernel_size,
                      strides=stride,
                      use_bias=False,
                      name=name + '_2_conv')(x)
    x = layers.BatchNormalization(name=name + '_2_bn')(x)
    x = layers.Activation('relu', name=name + '_2_relu')(x)

    x = layers.Conv2D(4 * filters, 1, name=name + '_3_conv')(x)
    x = layers.Add(name=name + '_out')([shortcut, x])
    return x

def stack2(x, filters, blocks, stride1=2, name=None):
    x = block2(x, filters, conv_shortcut=True, name=name + '_block1')
    for i in range(2, blocks):
        x = block2(x, filters, name=name + '_block' + str(i))
    x = block2(x, filters, stride=stride1, name=name + '_block' + str(blocks))
    return x

def ResNet50V2(include_top=True,  # 是否包含位于网络顶部的全连接层
               preact=True,  # 是否使用预激活
               use_bias=True,  # 是否对卷积层使用偏置
               weights='imagenet',
               input_tensor=None,  # 可选的keras张量，用作模型的图像输入
               input_shape=None,
               pooling=None,
               classes=1000,  # 用于分类图像的可选类数
               classifier_activation='softmax'):  # 分类层激活函数
                   
    img_input = layers.Input(shape=input_shape)
    x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)), name='conv1_pad')(img_input)
    x = layers.Conv2D(64, 7, strides=2, use_bias=use_bias, name='conv1_conv')(x)

    if not preact:
        x = layers.BatchNormalization(name='conv1_bn')(x)
        x = layers.Activation('relu', name='conv1_relu')(x)

    x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x)
    x = layers.MaxPooling2D(3, strides=2, name='pool1_pool')(x)

    x = stack2(x, 64, 3, name='conv2')
    x = stack2(x, 128, 4, name='conv3')
    x = stack2(x, 256, 6, name='conv4')
    x = stack2(x, 512, 3, stride1=1, name='conv5')

    if preact:
        x = layers.BatchNormalization(name='post_bn')(x)
        x = layers.Activation('relu', name='post_relu')(x)
    if include_top:
        x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
        x = layers.Dense(classes, activation=classifier_activation, name='predictions')(x)
    else:
        if pooling == 'avg':
            # GlobalAveragePooling2D就是将每张图片的每个通道值各自加起来再求平均，
            # 最后结果是没有了宽高维度，只剩下个数与平均值两个维度。
            # 可以理解为变成了多张单像素图片。
            x = layers.GlobalAveragePooling2D(name='avg_pool')(x)
        elif pooling == 'max':
            x = layers.GlobalMaxPooling2D(name='max_pool')(x)

    model = Model(img_input, x)
    return model

if __name__ == '__main__':
    model = ResNet50V2(input_shape=(224, 224, 3))
    model.summary()