Lenet5在CIFAR数据集上的分类问题

网络：

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

class Lenet5(nn.Module):
    """
    for cifar 10 dataset
    """
    def __init__(self):
        super(Lenet5, self).__init__()

        self.conv_unit = nn.Sequential(
            # x: [b, 3, 32, 32] => [b, 6, ]
            nn.Conv2d(3, 6, kernel_size=5, stride=1, padding=0),
            nn.AvgPool2d(kernel_size=2, stride=2, padding=0),

            nn.Conv2d(6, 16, kernel_size=5, stride=1, padding=0),
            nn.AvgPool2d(kernel_size=2, stride=2, padding=0),

        )
        #flatten
        #fc unit
        self.fc_unit = nn.Sequential(
            nn.Linear(16*5*5, 120),
            nn.ReLU(),
            nn.Linear(120, 84),
            nn.ReLU(),
            nn.Linear(84,10)
        )
        # 表示一个随机生成的tensor[b, 3, 32, 32]
        temp = torch.randn(2,3,32,32)
        out = self.conv_unit(temp)
        # [2, 16, 5, 5] 这属于测试了conv_unit的输出，那么flatten的数据就是16*5*5
        print('conv_out:', out.shape)

        # use 交叉熵损失
        #self.criteon = nn.MSELoss()
        #分类问题使用交叉熵，逼近使用MSE
        self.criteon = nn.CrossEntropyLoss()
        #这一整个函数直接包括了softmax过程+计算loss


    #backward不用写，往前走一遍，pytorch自动记录往前的路径，bk会自动往回走
    def forward(self, x):
        """
        :param x: [b, 3, 32, 32]
        :return:
        """
        batchsz = x.size(0)
        # size 返回一个list，[b, 3, 32, 32],取第0个，就是b
        # [b, 32, 32, 32] => [b, 16, 5, 5]
        x = self.conv_unit(x)
        # [b, 16, 5, 5] => [b, 16*5*5]
        #x = x.view(batchsz, -1)
        x = x.view(batchsz, 16*5*5) #这样更严谨，这样后面不一样就会报错
        # [b, 16*5*5] => [b, 10]
        logits = self.fc_unit(x)
        # softmax前一个变量称为logits
        # loggits: [b, 10]
        # pred = F.softmax(logits, dim=1)
        # loss = self.criteon(logits, y)
        return logits


def main():
    net = Lenet5()
    temp = torch.randn(2, 3, 32, 32)
    out = net(temp)
    # [2, 16, 5, 5] 这属于测试了conv_unit的输出，那么flatten的数据就是16*5*5
    print('lenet_out:', out.shape)

if __name__ == '__main__':
    main()

加载数据集

def main():
    batchsz = 32
    #太小就不稳定了，梯度计算是把当前batchsize的平均方向作为update的方向，太小就会具有随机性
    cifar_train = datasets.CIFAR10('cifar',True, transform=transforms.Compose([
        transforms.Resize((32, 32)),
        transforms.ToTensor()
    ]), 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()
    ]), download=True)
    cifar_test = DataLoader(cifar_test, batch_size=batchsz, shuffle=True)
    #########注意，第一个别填错，一开始天了cifar_train，也就是会去这边索引，但是呢，这个是个dataloader，是无法索引的！！

    x, label = iter(cifar_train).next()
    # inter把dataload的迭代器得到，使用next方法得到一个batch
    print('x:', x.shape, 'label', label.shape)

训练、测试

device = torch.device('cuda')
    model = Lenet5().to(device)
    print(model)

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

    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 长度为0的标量
            loss = criteon(logits, label)

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



        #对于标量，用item转化为numpy打印
        print(epoch, loss.item())

        model.eval()
        with torch.no_grad():
            # test 不需要计算梯度可以把它包在with里面,告诉计算机，不需要做backward
            total_correct = 0
            total_num = 0

            for x, label in cifar_test:
                x, label = x.to(device), label.to(device)

                #[b,10]
                logits = model(x)
                #输出在一维上面数据最大值所在的索引，索引是0~9
                ##dim = 1指定列，也就是行不变，列之间的比较
                pred = logits.argmax(dim=1)
                # [b] vs [b] => scalar tensor
                #[2]      [2]      [1]
                #[1]  eq  [2]  =>  [0]  sum => 1  这是一个三行一列的tensor
                #[2]      [0]      [0]
                total_correct += torch.eq(pred, label).float().sum().item()
                #item是转化为numpy的意思
                total_num += x.size(0)

            acc = total_correct / total_num
            print(epoch, acc)


if __name__ == '__main__':
    main()