Pytorch两种构建网络的方法

版本：Pytorch 1.0 代码是在jupter中执行的。

导包：

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms

设置超参：

BATCH_SIZE = 512 # 大概需要2G的显存
EPOCHS = 20 # 总共训练批次
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu") 

加载数据：

# 下载训练集
train_loader = torch.utils.data.DataLoader(
    datasets.MNIST('data', train = True, download = True,
              transform = transforms.Compose([
                  transforms.ToTensor(),
                  transforms.Normalize((0.1037,), (0.3081,))
              ])),
batch_size = BATCH_SIZE, shuffle = True)

# 测试集
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('data', train = False, transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1037,), (0.3081,))
])),
batch_size = BATCH_SIZE, shuffle = True)

构建网络：方式一

# 定义模型
class ConvNet(nn.Module):
    def __init__(self):
        super().__init__()
        #1*1*28*28
        self.conv1 = nn.Conv2d(1, 10, 5) 
        self.conv2 = nn.Conv2d(10, 20, 3) 
        self.fc1 = nn.Linear(20 * 10 * 10, 500)
        self.fc2 = nn.Linear(500, 10)
        
    def forward(self, x):
        in_size = x.size(0)
        out= self.conv1(x) # 1* 10 * 24 *24
        out = F.relu(out)
        out = F.max_pool2d(out, 2, 2) # 1* 10 * 12 * 12
        out = self.conv2(out) # 1* 20 * 10 * 10
        out = F.relu(out)
        out = out.view(in_size, -1) # 1 * 2000
        out = self.fc1(out) # 1 * 500
        out = F.relu(out)
        out = self.fc2(out) # 1 * 10
        out = F.log_softmax(out, dim = 1)
        return out

构建网络：方式二——把更多的内容放在了Sequential里面，觉得网络会显得清楚一些

class MyNet(torch.nn.Module):
    def __init__(self):  
        super(MyNet, self).__init__()  
        self.conv1 = nn.Sequential( # (1,28,28)  
                     nn.Conv2d(in_channels=1, out_channels=16, kernel_size=5,  
                               stride=1, padding=2), # (16,28,28)  
        # 想要con2d卷积出来的图片尺寸没有变化, padding=(kernel_size-1)/2  
                     nn.ReLU(),  
                     nn.MaxPool2d(kernel_size=2) # (16,14,14)  
                     )  
        self.conv2 = nn.Sequential( # (16,14,14)  
                     nn.Conv2d(16, 32, 5, 1, 2), # (32,14,14)  
                     nn.ReLU(),  
                     nn.MaxPool2d(2) # (32,7,7)  
                     )  
        self.out = nn.Linear(32*7*7, 10)  
  
    def forward(self, x):  
        x = self.conv1(x)  
        x = self.conv2(x)  
        x = x.view(x.size(0), -1) # 将（batch，32,7,7）展平为（batch，32*7*7）  
        output = self.out(x)  
        return output 

定义优化器：

#生成模型和优化器
model = MyNet().to(DEVICE)  # MyNet可以改为ConvNet 调用不同模型
optimizer = optim.Adam(model.parameters())

定义训练和测试函数：

# 定义训练函数
def train(model, device, train_loader, optimizer, epoch):
    model.train()  # 设置为trainning模式
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()  # 优化器梯度初始化为零
        output = model(data)  # 把数据输入网络并得到输出，即进行前向传播
        loss = F.cross_entropy(output, target)   # 定义损失函数
        loss.backward()  # 反向传播梯度
        optimizer.step()  # 结束一次前传+反传之后，更新参数
        if (batch_idx + 1) % 30 == 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()))
# 定义测试函数
def test(model, device, test_loader):
    model.eval()  # 设置为test模式
    test_loss =0  # 初始化测试损失值为0
    correct = 0  # 初始化预测正确的数据个数为0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)  #计算前要把变量变成Variable形式，因为这样子才有梯度
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction = 'sum') # 将一批的损失相加
            pred = output.max(1, keepdim = True)[1] # 找到概率最大的下标
            correct += pred.eq(target.view_as(pred)).sum().item()  # 对预测正确的数据个数进行累加
    
    test_loss /= len(test_loader.dataset)
    print("\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%) \n".format(
        test_loss, correct, len(test_loader.dataset),
        100.* correct / len(test_loader.dataset)
            ))

main函数

# 最后开始训练和测试
for epoch in range(1, EPOCHS + 1):
    train(model,  DEVICE, train_loader, optimizer, epoch)
    test(model, DEVICE, test_loader)