1.导入必要模块

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt

2.超参数设置

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')   #设备

input_size = 784      #输入大小
hidden_size = 500     #隐层大小
num_classes = 10      #输出大小
num_epochs = 2        #迭代次数
batch_size = 100      #批量大小
learning_rate = 0.001   #学习率

3.数据准备

train_dataset = torchvision.datasets.MNIST(root='./data',       #下载训练数据
                                          train = True,
                                          transform=transforms.ToTensor(),
                                          download=True)
test_dataset = torchvision.datasets.MNIST(root='./data',        #下载测试数据
                                         train = False,
                                         transform=transforms.ToTensor())

train_loader = torch.utils.data.DataLoader(dataset=train_dataset,     #制作DataLoader
                                          batch_size=batch_size,
                                          shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                         batch_size=batch_size,
                                         shuffle=False)

4.打印部分加载的数据

examples = iter(test_loader)    
example_data, example_targets = examples.next()

for i in range(6):
    plt.subplot(2, 3, i+1)
    plt.imshow(example_data[i][0], cmap='gray')
plt.show()

5.模型建立

class NeuralNet(nn.Module):
    def __init__(self, input_size, hidden_size, num_classes):
        super(NeuralNet, self).__init__()
        self.input_size = input_size
        self.l1 = nn.Linear(input_size, hidden_size)
        self.relu = nn.ReLU()
        self.l2 = nn.Linear(hidden_size, num_classes)
    
    def forward(self, x):
        out = self.l1(x)
        out = self.relu(out)
        out = self.l2(out)
        return out

6.训练

model = NeuralNet(input_size, hidden_size, num_classes).to(device)
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
n_total_steps = len(train_loader)

for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.reshape(-1, 28*28).to(device)
        labels = labels.to(device)
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        if (i+1)%100==0:
            print(f'Epoch [{epoch+1}/{num_epochs}], Step [{i+1}/{n_total_steps}], Loss:{loss.item():.4f}')

with torch.no_grad():
    n_correct = 0
    n_samples = 0
    for images, labels in test_loader:
        images = images.reshape(-1, 28*28).to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        n_samples += labels.size(0)
        n_correct += (predicted == labels).sum().item()
acc = 100.0*n_correct / n_samples
print(f'Accuracy of the network on the 1000 test images:{acc}%')