PyTorch实现用resnet18训练cifar数据集

随便记录一下自己的学习过程
train.py

import torch

from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision import transforms
from torch import nn, optim
from lenet5 import Lenet5
from resnet import ResNet18

def main():
    batch_size = 32
    # 这个是一次加载一张的数据，所以后续还要定义怎么按批次加载
    cifar_train = datasets.CIFAR10('cifar', True, transform=transforms.Compose([
        transforms.Resize((32, 32)), # 转换数据格式
        transforms.ToTensor(), # ToTensor，Tensor为计算的基本单元
        transforms.Normalize(
            mean=[0.485, 0.456, 0.406],
            std=[0.229, 0.224, 0.225]
        ) # 标准化，参数都是设定好的
    ]), download=True)
    # 数据加载器，# shuffle设置随机化
    cifar_train = DataLoader(cifar_train, batch_size=batch_size, shuffle=True)

    cifar_test = datasets.CIFAR10('cifar', False, transform=transforms.Compose([
        transforms.Resize((32, 32)),  # 转换数据格式
        transforms.ToTensor(),
        transforms.Normalize(
            mean=[0.485, 0.456, 0.406],
            std=[0.229, 0.224, 0.225]
        ) # 标准化
    ]), download=True)
    cifar_test = DataLoader(cifar_test, batch_size=batch_size, shuffle=True)  # shuffle设置随机化

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

    device = torch.device('cuda') # 命名一个GPU设备
    #model = Lenet5().to(device)
    model = ResNet18().to(device) # 将模型导入到GPU
    criteon = nn.CrossEntropyLoss().to(device)
    print(model)
    optimizer = optim.Adam(model.parameters(), lr=1e-3) # 定义优化器

    for epoch in range(1000):
        model.train() # 将模型变为训练模式
        for batch_index, (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)

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

        print(epoch, loss.item())

        model.eval() # 将模型变为测试模式
        with torch.no_grad(): # 告诉torch不需要计算梯度
            # 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
                total_correct += torch.eq(pred, label).float().sum().item()
                total_num += x.size(0)

            acc = total_correct / total_num
            print("test", epoch, acc)

if __name__ == '__main__':
    main()

同目录下的resnet.py

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

class ResBlk(nn.Module):
    """
    resnet block
    """

    def __init__(self, ch_in, ch_out, stride=1):
        """

        :param ch_in:
        :param ch_out:
        """
        super(ResBlk, self).__init__()

        self.conv1 = nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=stride, padding=1)
        self.bn1 = nn.BatchNorm2d(ch_out)
        self.conv2 = nn.Conv2d(ch_out, ch_out, kernel_size=3, stride=1, padding=1)
        self.bn2 = nn.BatchNorm2d(ch_out)

        # 如果形状不一样就改成一样的
        self.extra = nn.Sequential()
        if ch_out != ch_in:
            # [b, ch_in, h, w] => [b, ch_out, h, w]
            self.extra = nn.Sequential(
                nn.Conv2d(ch_in, ch_out, kernel_size=1, stride=stride),
                nn.BatchNorm2d(ch_out)
            )

    def forward(self, x):
        """

        :param x: [b, ch, h, w]
        :return:
        """
        out = F.relu(self.bn1(self.conv1(x)))
        out = self.bn2(self.conv2(out))
        # short cut
        # element-wise add: [b, ch_in, h, w] wit [b, ch_out, h, w]
        out = self.extra(x) + out
        out = F.relu(out)
        return out


class ResNet18(nn.Module):
    def __init__(self):
        super(ResNet18, self).__init__()

        # 预处理层
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, stride=3, padding=0),
            nn.BatchNorm2d(64)
        )
        # followed 4 blocks
        # [b, 64, h, w] => [b, 128, h, w]
        self.blk1 = ResBlk(64, 128, stride=2)
        # [b, 128, h, w] => [b, 256, h, w]
        self.blk2 = ResBlk(128, 256, stride=2)
        # [b, 256, h, w] => [b, 512, h, w]
        self.blk3 = ResBlk(256, 512, stride=2)
        # [b, 512, h, w] => [n, 1024, h, w]
        self.blk4 = ResBlk(512, 512, stride=2)

        self.outlayer = nn.Linear(512*1*1, 10)

    def forward(self, x):
        """

        :param x:
        :return:
        """
        x = F.relu(self.conv1(x))

        # [b, 64, h, w] => [b, 1024, h, w]
        x = self.blk1(x)
        x = self.blk2(x)
        x = self.blk3(x)
        x = self.blk4(x)

        #print("after conv:", x.shape) # [b, 512, 2, 2]
        # [b, 512, 2, 2] => [b, 512, 1, 1]
        x = F.adaptive_avg_pool2d(x, [1, 1])
        #print("after pool:", x.shape) # [b, 512, 1, 1]
        # [b, 512, 1, 1] => [b, 512]
        x = x.view(x.size(0), -1)
        x = self.outlayer(x)

        return x

def main():
    blk = ResBlk(64, 128, stride=2)
    tmp = torch.randn(2, 64, 32, 32)
    out = blk(tmp)
    print("block: ", out.shape)

    x = torch.randn(2, 3, 32, 32)
    model = ResNet18()
    out = model(x)
    print("resnet:", out.shape)

if __name__ == '__main__':
    main()