deep_residual_network

# ---------------------------------------------------------------------------- #
# An implementation of https://arxiv.org/pdf/1512.03385.pdf                    #
# See section 4.2 for the model architecture on CIFAR-10                       #
# ---------------------------------------------------------------------------- #

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms

# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')


# Hyper-parameters
num_epochs = 80
learning_rate = 0.001


# Image preprocessing modules
transform = transforms.Compose([        # 将多个transform组合起来使用
    transforms.Pad(4),                  # 由于上下左右都要填充4个像素
    transforms.RandomHorizontalFlip(),  # 随机水平翻转给定的Image,概率为0.5
    transforms.RandomCrop(32),          # 依据给定的32随机裁剪,32x32
    transforms.ToTensor()])

# CIFAR-10 dataset
train_dataset = torchvision.datasets.CIFAR10(root='../data/',
                                             train=True,
                                             transform=transform,
                                             download=True)
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,
                                           shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=100,
                                          shuffle=False)

# 3x3 convolution
def conv3x3(in_channels, out_channels, stride=1):  # 卷积输入输出的尺寸
    return nn.Conv2d(in_channels, out_channels, kernel_size=3,
                     stride=stride, padding=1, bias=False)

# Residual block残差块
class ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
        super(ResidualBlock, self).__init__()
        self.conv1 = conv3x3(in_channels, out_channels, stride)
        self.bn1 = nn.BatchNorm2d(out_channels)   # 使用归一化防止提取的特征遭到破坏
        self.relu = nn.ReLU(inplace=True)         #
        self.conv2 = conv3x3(out_channels,out_channels)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.downsample = downsample

    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:
            residual = self.downsample(x) # 为什么是对x下采样
        out += residual                   # 这一步作用
        out = self.relu(out)
        return out


# ResNet
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)                   # 输入层
        self.bn = nn.BatchNorm2d(16)                # 16表示归一化期望输入的特征数
        self.relu = nn.ReLU(inplace=True)           # 上层网络传递下来的tensor原地操作，不用存储变量，节省运算内存
        self.layer1 = self.make_layer(block, 16, layers[0])
        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):
            downsample = nn.Sequential(
                conv3x3(self.in_channels, out_channels, stride=stride),
                nn.BatchNorm2d(out_channels))
        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)  # 池化层输出维度为4的batch；即（batchsize，channels，x，y）；out.size(0)是指batchsize的值，self.view(out.size(0), -1)指转换有几行，-1指在不告诉函数有多少列的情况下，根据原tensor数据和batchsize自动分配列数。
        out = self.fc(out)
        return out

model = ResNet(ResidualBlock, [2,2,2]).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()       # 交叉熵
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# For updating learning rate
def update_lr(optimizer, lr):
    for param_group in optimizer.param_groups:
        param_group['lr'] = lr

# Train the model
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)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        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:
        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))

# Save the model checkpoint
torch.save(model.state_dict(), 'resnet.ckpt')