Python 下载 MINIST 数据集 -- 解决代理问题

data.py

import matplotlib.pyplot as plt
import torch
import torchvision
from torch.utils.data import DataLoader

# 代理部分
import urllib.request
handler = urllib.request.ProxyHandler(
    {'https': 'https://xx:$zz@proxy.yy.com:8080'}) # also https
opener = urllib.request.build_opener(handler)
urllib.request.install_opener(opener)

batch_size_train = 64
batch_size_test = 1000
random_seed = 1
torch.manual_seed(random_seed)

train_loader = torch.utils.data.DataLoader(
    torchvision.datasets.MNIST('./data/', train=True, download=True,
                               transform=torchvision.transforms.Compose([
                                   torchvision.transforms.ToTensor(),
                                   torchvision.transforms.Normalize(
                                          (0.1307,), (0.3081,))
                               ])),
    batch_size=batch_size_train, shuffle=True)
test_loader = torch.utils.data.DataLoader(
    torchvision.datasets.MNIST('./data/', train=False, download=True,
                               transform=torchvision.transforms.Compose([
                                   torchvision.transforms.ToTensor(),
                                   torchvision.transforms.Normalize(
                                         (0.1307,), (0.3081,))
                               ])),
    batch_size=batch_size_test, shuffle=True)

examples = enumerate(test_loader)
batch_idx, (example_data, example_targets) = next(examples)
print(example_targets)
print(example_data.shape)

fig = plt.figure()
for i in range(6):
    plt.subplot(2, 3, i+1)
    plt.tight_layout()
    plt.imshow(example_data[i][0], cmap='gray', interpolation='none')
    plt.title("Ground Truth: {}".format(example_targets[i]))
    plt.xticks([])
    plt.yticks([])
    plt.show()

net.py

import matplotlib.pyplot as plt
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

from data import train_loader, test_loader


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return F.log_softmax(x)


n_epochs = 3
learning_rate = 0.01
momentum = 0.5
log_interval = 10
network = Net()
optimizer = optim.SGD(network.parameters(), lr=learning_rate,
                      momentum=momentum)

train_losses = []
train_counter = []
test_losses = []
test_counter = [i*len(train_loader.dataset) for i in range(n_epochs + 1)]


def train(epoch):
    network.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        optimizer.zero_grad()
        output = network(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % log_interval == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.item()))
            train_losses.append(loss.item())
            train_counter.append(
                (batch_idx*64) + ((epoch-1)*len(train_loader.dataset)))
            torch.save(network.state_dict(), './model.pth')
            torch.save(optimizer.state_dict(), './optimizer.pth')


train(1)


def test():
    network.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            output = network(data)
            test_loss += F.nll_loss(output, target, size_average=False).item()
            pred = output.data.max(1, keepdim=True)[1]
            correct += pred.eq(target.data.view_as(pred)).sum()
    test_loss /= len(test_loader.dataset)
    test_losses.append(test_loss)
    print('\nTest set: Avg. loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))


test()

for epoch in range(1, n_epochs + 1):
    train(epoch)
    test()


fig = plt.figure()
plt.plot(train_counter, train_losses, color='blue')
plt.scatter(test_counter, test_losses, color='red')
plt.legend(['Train Loss', 'Test Loss'], loc='upper right')
plt.xlabel('number of training examples seen')
plt.ylabel('negative log likelihood loss')
plt.show()

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()   # 继承__init__功能
        ## 第一层卷积
        self.conv1 = nn.Sequential(
            # 输入[1,28,28]
            nn.Conv2d(
                in_channels=1,    # 输入图片的高度
                out_channels=16,  # 输出图片的高度
                kernel_size=5,    # 5x5的卷积核，相当于过滤器
                stride=1,         # 卷积核在图上滑动，每隔一个扫一次
                padding=2,        # 给图外边补上0
            ),
            # 经过卷积层 输出[16,28,28] 传入池化层
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2)   # 经过池化 输出[16,14,14] 传入下一个卷积
        )
        ## 第二层卷积
        self.conv2 = nn.Sequential(
            nn.Conv2d(
                in_channels=16,    # 同上
                out_channels=32,
                kernel_size=5,
                stride=1,
                padding=2
            ),
            # 经过卷积 输出[32, 14, 14] 传入池化层
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2)  # 经过池化 输出[32,7,7] 传入输出层
        )
        ## 输出层
        self.output = nn.Linear(in_features=32*7*7, out_features=10)

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)           # [batch, 32,7,7]
        x = x.view(x.size(0), -1)   # 保留batch, 将后面的乘到一起 [batch, 32*7*7]
        output = self.output(x)     # 输出[50,10]
        return output