PyTorch实现ResNet18

论文链接：Deep residual learning for image recognition
译文地址：http://blog.csdn.net/wspba/article/details/57074389
解读博客：https://blog.csdn.net/wspba/article/details/57074389
Resnet 网络简介：

ResNet-18结构为例：

基本结点：

代码实现：

import torch
import torch.nn as nn
from torch.nn import functional as F


class RestNetBasicBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride):
        super(RestNetBasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=stride, padding=1)
        self.bn2 = nn.BatchNorm2d(out_channels)

    def forward(self, x):
        output = self.conv1(x)
        output = F.relu(self.bn1(output))
        output = self.conv2(output)
        output = self.bn2(output)
        return F.relu(x + output)


class RestNetDownBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride):
        super(RestNetDownBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride[0], padding=1)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=stride[1], padding=1)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.extra = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride[0], padding=0),
            nn.BatchNorm2d(out_channels)
        )

    def forward(self, x):
        extra_x = self.extra(x)
        output = self.conv1(x)
        out = F.relu(self.bn1(output))

        out = self.conv2(out)
        out = self.bn2(out)
        return F.relu(extra_x + out)


class RestNet18(nn.Module):
    def __init__(self):
        super(RestNet18, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)
        self.bn1 = nn.BatchNorm2d(64)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

        self.layer1 = nn.Sequential(RestNetBasicBlock(64, 64, 1),
                                    RestNetBasicBlock(64, 64, 1))

        self.layer2 = nn.Sequential(RestNetDownBlock(64, 128, [2, 1]),
                                    RestNetBasicBlock(128, 128, 1))

        self.layer3 = nn.Sequential(RestNetDownBlock(128, 256, [2, 1]),
                                    RestNetBasicBlock(256, 256, 1))

        self.layer4 = nn.Sequential(RestNetDownBlock(256, 512, [2, 1]),
                                    RestNetBasicBlock(512, 512, 1))

        self.avgpool = nn.AdaptiveAvgPool2d(output_size=(1, 1))

        self.fc = nn.Linear(512, 10)

    def forward(self, x):
        out = self.conv1(x)
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = self.avgpool(out)
        out = out.reshape(x.shape[0], -1)
        out = self.fc(out)
        return out

用来预测CIFAR-10数据集
数据集：
官网链接：CIFAR-10 DATASET

测试代码：

import torch
from torch import nn, optim
import torchvision.transforms as transforms
from torchvision import datasets
from torch.utils.data import DataLoader
from restnet18.restnet18 import RestNet18


#  用CIFAR-10 数据集进行实验

def main():
    batchsz = 128

    cifar_train = datasets.CIFAR10('cifar', True, transform=transforms.Compose([
        transforms.Resize((32, 32)),
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485, 0.456, 0.406],
                             std=[0.229, 0.224, 0.225])
    ]), download=True)
    cifar_train = DataLoader(cifar_train, batch_size=batchsz, shuffle=True)

    cifar_test = datasets.CIFAR10('cifar', False, transform=transforms.Compose([
        transforms.Resize((32, 32)),
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485, 0.456, 0.406],
                             std=[0.229, 0.224, 0.225])
    ]), download=True)
    cifar_test = DataLoader(cifar_test, batch_size=batchsz, shuffle=True)

    x, label = iter(cifar_train).next()
    print('x:', x.shape, 'label:', label.shape)

    device = torch.device('cuda')
    # model = Lenet5().to(device)
    model = RestNet18().to(device)

    criteon = nn.CrossEntropyLoss().to(device)
    optimizer = optim.Adam(model.parameters(), lr=1e-3)
    print(model)

    for epoch in range(1000):

        model.train()
        for batchidx, (x, label) in enumerate(cifar_train):
            # [b, 3, 32, 32]
            # [b]
            x, label = x.to(device), label.to(device)

            logits = model(x)
            # logits: [b, 10]
            # label:  [b]
            # loss: tensor scalar
            loss = criteon(logits, label)

            # backprop
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

        print(epoch, 'loss:', loss.item())

        model.eval()
        with torch.no_grad():
            # test
            total_correct = 0
            total_num = 0
            for x, label in cifar_test:
                # [b, 3, 32, 32]
                # [b]
                x, label = x.to(device), label.to(device)

                # [b, 10]
                logits = model(x)
                # [b]
                pred = logits.argmax(dim=1)
                # [b] vs [b] => scalar tensor
                correct = torch.eq(pred, label).float().sum().item()
                total_correct += correct
                total_num += x.size(0)
                # print(correct)

            acc = total_correct / total_num
            print(epoch, 'test acc:', acc)


if __name__ == '__main__':
    main()

运行结果：