CIFAR-10分类（pytorch）

import torch
from torch.autograd import Variable
import torch.nn as nn
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt

EPOCH = 50
LR = 0.001
BATCH_SIZE = 50
DOWNLOAD_CIFAR = False #如果没下载数据集就设成True

transform = torchvision.transforms.Compose(
    [torchvision.transforms.ToTensor(),
     torchvision.transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]
)

trainset = torchvision.datasets.CIFAR10(
    root='./CIFAR10',
    train=True,
    transform=transform,
    download=DOWNLOAD_CIFAR
)

train_loader = Data.DataLoader(dataset=trainset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(
    root='./CIFAR10',
    train=False,
    transform=transform,
    download=DOWNLOAD_CIFAR
)

test_loader = Data.DataLoader(dataset=testset, batch_size=BATCH_SIZE, shuffle=False, num_workers=2)

classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck') #这一步好像不是必须的

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential( #32*32
            nn.Conv2d(
                in_channels=3,
                out_channels=16,
                kernel_size=5,
                stride=1,
                padding=2
            ),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2)
         )
        self.conv2 = nn.Sequential(
            nn.Conv2d(16, 32, 5, 1, 2),
            nn.ReLU(),
            nn.MaxPool2d(2)
            )
        self.out = nn.Linear(32*8*8, 10)
    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)
        output = self.out(x)
        return output


cnn = CNN()
optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)
loss_func = nn.CrossEntropyLoss()
loss_list = []
accuracy_list = []

if __name__ == '__main__':
    for epoch in range(EPOCH):
        for step, (x, y) in enumerate(train_loader):
            b_x = Variable(x)
            b_y = Variable(y)
            outputs = cnn(b_x)
            loss = loss_func(outputs, b_y)
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

            if step % 50 == 0:
                loss_list.append(loss)
                print('epoch: ', epoch, '| step: ', step, '| loss: %.4f' % loss.item())

    for step, (t_x, t_y) in enumerate(test_loader):
        t_x = Variable(t_x)
        t_y = Variable(t_y)
        test_out = cnn(t_x)
        pred_y = torch.max(test_out, 1)[1].data.squeeze()
        accuracy = sum(pred_y == t_y).type(torch.FloatTensor)/t_y.size(0)
        accuracy_list.append(accuracy)
        print('step: ', step, '| accurary: %.4f' % accuracy)

    plt.figure()
    plt.plot(loss_list)
    plt.figure()
    plt.plot(accuracy_list)
    plt.show()
    

这个模型的训练效果不大好
loss

accuracy