深度学习----第J2周：ResNet50V2算法实现

---

前言

• 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
• ** 参考文章：Pytorch实战 | 第P5周：运动鞋识别**
• 🍖 原作者：K同学啊|接辅导、项目定制

---

一、ResNetV2与ResNet结构对比

• 在阅读原论文中，主要区别就是残差结构的不通过，我们可以发现新的结构先进行BN和激活函数计算后卷积，把addition后的ReLU计算放到残差结构内部。
  

二、模型复现

2.1 Residual Block

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

2.2 堆叠的 Residual Block

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

2.3 ResNet50V2

def ResNet50V2(include_top=True,
               preact=True,
               use_bias=True,
               weights='imagenet',
               input_tensor=None,
               input_shape=None,
               pooling=None,
               classes=1000,
               classifier_activation='softmax'):
    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':

            x = layers.GlobalAveragePooling2D(name='avg_pool')(x)

        elif pooling == 'max':

            x = layers.GlobalMaxPooling2D(name='max_pool')(x)

    model = Model(img_input, x)

    return model

2.4 查看模型结构

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

部分结构如下:

2.5 tf下全部代码

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


# Residual Block
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


# 堆叠的 Residual Block
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


# ResNet50V2
def ResNet50V2(include_top=True,
               preact=True,
               use_bias=True,
               weights='imagenet',
               input_tensor=None,
               input_shape=None,
               pooling=None,
               classes=1000,
               classifier_activation='softmax'):
    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':

            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()

三、Pytorch复现

3.1 代码实现

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os, PIL, pathlib, warnings
from torchsummary import summary


#忽略警告信息
warnings.filterwarnings("ignore")

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

"""
Residual Block
"""


class Block2(nn.Module):
    def __init__(self, in_channel, filters, kernel_size=3, stride=1, conv_shortcut=False):
        super(Block2, self).__init__()
        self.preact = nn.Sequential(
            nn.BatchNorm2d(in_channel),
            nn.ReLU(True)
        )

        self.shortcut = conv_shortcut
        if self.shortcut:
            self.short = nn.Conv2d(in_channel, 4*filters, 1, stride=stride, padding=0, bias=False)
        elif stride>1:
            self.short = nn.MaxPool2d(kernel_size=1, stride=stride, padding=0)
        else:
            self.short = nn.Identity()

        self.conv1 = nn.Sequential(
            nn.Conv2d(in_channel, filters, 1, stride=1, bias=False),
            nn.BatchNorm2d(filters),
            nn.ReLU(True)
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(filters, filters, kernel_size, stride=stride, padding=1, bias=False),
            nn.BatchNorm2d(filters),
            nn.ReLU(True)
        )
        self.conv3 = nn.Conv2d(filters, 4*filters, 1, stride=1, bias=False)

    def forward(self, x):
        x1 = self.preact(x)
        if self.shortcut:
            x2 = self.short(x1)
        else:
            x2 = self.short(x)
        x1 = self.conv1(x1)
        x1 = self.conv2(x1)
        x1 = self.conv3(x1)
        x = x1 + x2
        return x


class Stack2(nn.Module):
    def __init__(self, in_channel, filters, blocks, stride=2):
        super(Stack2, self).__init__()
        self.conv = nn.Sequential()
        self.conv.add_module(str(0), Block2(in_channel, filters, conv_shortcut=True))
        for i in range(1, blocks-1):
            self.conv.add_module(str(i), Block2(4*filters, filters))
        self.conv.add_module(str(blocks-1), Block2(4*filters, filters, stride=stride))

    def forward(self, x):
        x = self.conv(x)
        return x


"""
构建ResNet50V2
"""


class ResNet50V2(nn.Module):
    def __init__(self,
                 include_top=True,  # 是否包含位于网络顶部的全链接层
                 preact=True,  # 是否使用预激活
                 use_bias=True,  # 是否对卷积层使用偏置
                 input_shape=[224, 224, 3],
                 classes=1000,
                 pooling=None):  # 用于分类图像的可选类数
        super(ResNet50V2, self).__init__()

        self.conv1 = nn.Sequential()
        self.conv1.add_module('conv', nn.Conv2d(3, 64, 7, stride=2, padding=3, bias=use_bias, padding_mode='zeros'))
        if not preact:
            self.conv1.add_module('bn', nn.BatchNorm2d(64))
            self.conv1.add_module('relu', nn.ReLU())
        self.conv1.add_module('max_pool', nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

        self.conv2 = Stack2(64, 64, 3)
        self.conv3 = Stack2(256, 128, 4)
        self.conv4 = Stack2(512, 256, 6)
        self.conv5 = Stack2(1024, 512, 3, stride=1)

        self.post = nn.Sequential()
        if preact:
            self.post.add_module('bn', nn.BatchNorm2d(2048))
            self.post.add_module('relu', nn.ReLU())
        if include_top:
            self.post.add_module('avg_pool', nn.AdaptiveAvgPool2d((1, 1)))
            self.post.add_module('flatten', nn.Flatten())
            self.post.add_module('fc', nn.Linear(2048, classes))
        else:
            if pooling=='avg':
                self.post.add_module('avg_pool', nn.AdaptiveAvgPool2d((1, 1)))
            elif pooling=='max':
                self.post.add_module('max_pool', nn.AdaptiveMaxPool2d((1, 1)))

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = self.conv3(x)
        x = self.conv4(x)
        x = self.conv5(x)
        x = self.post(x)
        return x


model = ResNet50V2().to(device)
summary(model, (3, 224, 224))

3.2 结构打印

网络结构部分如下

---