ResNet和LeNet在CIFAR10数据集上的实战

主函数

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():
    batchsz = 128

    cifar_train = datasets.CIFAR10('cifar', True, transform=transforms.Compose([
        transforms.Resize((32, 32)),
        transforms.ToTensor(),
        #transforms.RandomRotation(15),	# -5<°0<15°
        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],	#分别代表RGB三个通道上的像素均值
                             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" if torch.cuda.is_available() else "cpu")
    # model = Lenet5().to(device)
    model = ResNet18().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，这块在forward的时候不需要构建计算图
            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()	# 转换为numpy
                total_correct += correct
                total_num += x.size(0)
                # print(correct)

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



if __name__ == '__main__':
    main()

LeNet模块

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


class Lenet5(nn.Module):
    """
    for cifar10 dataset.
    """
    def __init__(self):
        super(Lenet5, self).__init__()

        self.conv_unit = nn.Sequential(
            # x: [b, 3, 32, 32] => [b, 16, ]
            nn.Conv2d(3, 16, kernel_size=5, stride=1, padding=0),
            nn.MaxPool2d(kernel_size=2, stride=2, padding=0),
            #
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=0),
            nn.MaxPool2d(kernel_size=2, stride=2, padding=0),
            #
        )
        # flatten
        # fc unit
        self.fc_unit = nn.Sequential(
            nn.Linear(32*5*5, 32),	# nn开头的是类需要初始化，而F.开头的是函数，不需要初始化
            nn.ReLU(),
            # nn.Linear(120, 84),
            # nn.ReLU(),
            nn.Linear(32, 10)
        )


        # [b, 3, 32, 32]
        tmp = torch.randn(2, 3, 32, 32)
        out = self.conv_unit(tmp)
        # [b, 16, 5, 5]
        print('conv out:', out.shape)

        # # use Cross Entropy Loss
        # self.criteon = nn.MSELoss()
        # self.criteon = nn.CrossEntropyLoss()
       

    def forward(self, x):
        """

        :param x: [b, 3, 32, 32]
        :return:
        """
        batchsz = x.size(0)
        # [b, 3, 32, 32] => [b, 16, 5, 5]
        x = self.conv_unit(x)
        # [b, 16, 5, 5] => [b, 16*5*5]
        x = x.view(batchsz, 32*5*5)
        # [b, 16*5*5] => [b, 10]
        logits = self.fc_unit(x)

        # # [b, 10] 在10这个维度上做交叉熵
        # pred = F.softmax(logits, dim=1)	# 在pytorch里cross_entropy=softmax+log+null_loss
        # loss = self.criteon(logits, y)

        return logits

def main():

    net = Lenet5()

    tmp = torch.randn(2, 3, 32, 32)
    out = net(tmp)
    print('lenet out:', out.shape)




if __name__ == '__main__':
    main()

1. 在pytorch里cross_entropy = softmax+log+null_loss；

F.cross_entropy(logits, y)
'''相等于'''
pred = F.softmax(logits, dim=1)
pred_log = torch.log(pred)
F.nll_cross(pred_log, y)

在pytorch里没有展平这样的类，而nn.Sequential()里需要都是类，所以要不自己写个类，要不就是断开两个sequential，中间用view前向传播连起来；

class Flatten(nn.Module):

    def __init__(self):
        super(Flatten, self).__init__()

    def forward(self, input):
        return input.view(input.size(0), -1)

ResNet模块

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__()

        # we add stride support for resbok, which is distinct from tutorials; stride=2时32×32传进来大概变成16×16
        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)
        
		# 改变一下通道数，后面做相加的时候使通道数一样，比如上面两部分32×32和16×16相加
        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.
        # extra module: [b, ch_in, h, w] => [b, ch_out, h, w]
        # element-wise add:
        out = self.extra(x) + out
        out = F.relu(out)
        return out


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

        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] => [b, 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, h, w] => [b, 512, 1, 1]；不管输入为多少，最后会变成指定的一个像素
        x = F.adaptive_avg_pool2d(x, [1, 1])
        # print('after pool:', x.shape)
        
        x = x.view(x.size(0), -1)	# flatten操作
        x = self.outlayer(x)
        return x


def main():
    blk = ResBlk(64, 128, stride=4)
    tmp = torch.randn(2, 64, 32, 32)
    out = blk(tmp)
    print('block:', out.shape)

    x = torch.randn(2, 3, 32, 32)	# (batchsz, channel, h, w)
    model = ResNet18()
    out = model(x)
    print('resnet:', out.shape)


if __name__ == '__main__':
    main()

Tensor操作