学习笔记-PyTorch实现ResNet

代码来源：PyTorch学习仓库：https://github.com/yunjey/pytorch-tutorial
Resnet是何神提出的深度残差网络，旨在减少网络深度对过拟合的影响，采用深度残差进行网络学习F(x)-x
在进行代码编写的时候，注意resnet的几个小点：
1.由于我这里只用了basicblock，也只写了basicblock，restnet50及以上使用了bottleblock。这里代码可以看做是resnet最初级的版本吧
2.看代码的时候，downsample很难理解，要结合网络的结构，downsample是在输入维度和输出维度不一致时，进行的下采样操作

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(device)
num_epochs = 80
learning_rate = 0.001

transform = transforms.Compose([
    transforms.Pad(4),#将给定的所有边用给定的pad value填充
    transforms.RandomHorizontalFlip(),#随机水平翻转给定的图片，概率为0.5
    transforms.RandomCrop(32),#切割点位置随机选取
    transforms.ToTensor()])
# CIFAR-10 dataset
train_dataset = torchvision.datasets.CIFAR10(root='./data/', #存放根目录位置
                                             train=True,  #下载训练集
                                             transform=transform, #图片预处理方式
                                             download=True) #判断是否下载，如果下载过就不下载
test_dataset = torchvision.datasets.CIFAR10(root='./data/',
                                            train=False,
                                            transform=transforms.ToTensor())
# Data loader
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=100, #每个batch加载多少个样本
                                           shuffle=True)  #设置为True时会在每个epoch重新打乱数据
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=100,
                                          shuffle=False)
# def imshow(img):
#
#     npimg = img.numpy()
#     plt.imshow(np.transpose(npimg,(1,2,0)))
#     plt.show()
# dataiter = iter(train_loader)
# images,labels = dataiter.next()
# print(labels)
# imshow(torchvision.utils.make_grid(images))
def conv3x3(in_channels,out_channels,stride=1):
    return nn.Conv2d(in_channels,out_channels,kernel_size=3,stride=stride,padding=1,bias=False)#bias是否添加偏置
class ResidualBlock(nn.Module):#
    def __init__(self,in_channels,out_channels,stride=1,downsample=None):#默认不进行下采样
        super(ResidualBlock,self).__init__()
        self.conv1 = conv3x3(in_channels,out_channels,stride)
        self.bn1=nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(out_channels, out_channels)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.downsample = downsample #shortcut操作
    def forward(self,x):
        residual = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        if self.downsample:#当shortcut存在的时候
            residual = self.downsample(x)
            #我们将上一层的输出x输入进这个downsample所拥有的一些操作（卷积等），将结果赋给residual
            #简单说，这个目的就是为了应对上下层输出输入深度不一致问题
        out+=residual #将bn2的输出和shortcut过来加一起
        out = self.relu(out)
        return out

class ResNet(nn.Module):
    def __init__(self,block,layers,num_classes=10):
        super(ResNet,self).__init__()
        self.in_channels=16
        self.conv = conv3x3(3,16)
        self.bn = nn.BatchNorm2d(16)
        self.relu = nn.ReLU(inplace=True)
        self.layer1 = self.make_layer(block,16,layers[0]) #layers[0]次数的block操作
        self.layer2 = self.make_layer(block,32,layers[1],2)
        self.layer3 = self.make_layer(block,64,layers[2],2)
        self.avg_pool = nn.AvgPool2d(8)
        self.fc = nn.Linear(64,num_classes)
    def make_layer(self,block,out_channels,blocks,stride=1):
        downsample = None
        if(stride !=1)or(self.in_channels!=out_channels): #如果步长不等于1或者输入通道不等于输出通道时
            downsample = nn.Sequential(
                conv3x3(self.in_channels,out_channels,stride=stride),
                nn.BatchNorm2d(out_channels)#通过下采样使得通道数一致
            )
        layers = []
        layers.append(block(self.in_channels,out_channels,stride,downsample))
        self.in_channels = out_channels
        for i in range(1,blocks):
            layers.append(block(out_channels,out_channels))
        return nn.Sequential(*layers)
    def forward(self,x):
        out = self.conv(x)
        out = self.bn(out)
        out = self.relu(out)
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.avg_pool(out)
        out = out.view(out.size(0),-1)
        out = self.fc(out)
        return out
model = ResNet(ResidualBlock,[2,2,2]).to(device)

criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(),lr=learning_rate)

#自动更新权重
def update_lr(optimizer,lr):
    for param_group in optimizer.param_groups:
        param_group['lr'] = lr
total_step = len(train_loader)
curr_lr = learning_rate
for epoch in range(num_epochs):
    for i,(images,labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)

        outputs = model(images)
        loss = criterion(outputs, labels)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        if (i + 1) % 100 == 0:
            print("Epoch [{}/{}], Step [{}/{}] Loss: {:.4f}"
                  .format(epoch + 1, num_epochs, i + 1, total_step, loss.item()))
            # Decay learning rate
        if (epoch + 1) % 20 == 0: #每20回合学习率减少三分之一
            curr_lr /= 3
            update_lr(optimizer, curr_lr)
# Test the model
model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()
    print('Accuracy of the model on the test images: {} %'.format(100 * correct / total))