6 Pytorch实例——多GPU训练CIFAR10数据集（基于深度Resnet网络）

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms


# GPU设置（没有GPU就用cpu进行运算）
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

# 设置超参数Hyper-parameters
num_epochs = 80
learning_rate = 0.001

# 图像预处理模块，用于扩充数据（样本多样性）
transform = transforms.Compose([
    transforms.Pad(4),  #上下左右填充4个像素
    transforms.RandomHorizontalFlip(),  #依据概率对PIL图片进行水平翻转，默认概率为50%
    transforms.RandomCrop(32),  #依据给定的size随机裁剪
    transforms.ToTensor()])

# 加载CIFAR-10数据集
train_dataset = torchvision.datasets.CIFAR10(root='data/',
                                             train=True, 
                                             transform=transform,
                                             download=True)

test_dataset = torchvision.datasets.CIFAR10(root='data/',
                                            train=False, 
                                            transform=transforms.ToTensor())

train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=300, 
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=300, 
                                          shuffle=False)

# 3x3卷积 convolution
def conv3x3(in_channels, out_channels, stride=1):
    return nn.Conv2d(in_channels, out_channels, kernel_size=3, 
                     stride=stride, padding=1, bias=False)

# 残差模块 Residual block
class ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
        super(ResidualBlock, self).__init__()
        self.conv1 = conv3x3(in_channels, out_channels, stride)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(out_channels, out_channels)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.downsample = downsample
        
    def forward(self, x):
        residual = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        if self.downsample:
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out

# 残差网络 ResNet
class ResNet(nn.Module):
    def __init__(self, block, layers, num_classes=10):
        super(ResNet, self).__init__()
        self.in_channels = 16
        self.conv = conv3x3(3, 16)
        self.bn = nn.BatchNorm2d(16)
        self.relu = nn.ReLU(inplace=True)
        self.layer1 = self.make_layer(block, 16, layers[0])
        self.layer2 = self.make_layer(block, 32, layers[1], 2)
        self.layer3 = self.make_layer(block, 64, layers[2], 2)
        self.avg_pool = nn.AvgPool2d(8)
        self.fc = nn.Linear(64, num_classes)
        
    def make_layer(self, block, out_channels, blocks, stride=1):
        downsample = None
        if (stride != 1) or (self.in_channels != out_channels):
            downsample = nn.Sequential(
                conv3x3(self.in_channels, out_channels, stride=stride),
                nn.BatchNorm2d(out_channels))
        layers = []
        layers.append(block(self.in_channels, out_channels, stride, downsample))
        self.in_channels = out_channels
        for i in range(1, blocks):
            layers.append(block(out_channels, out_channels))
        return nn.Sequential(*layers)
    
    def forward(self, x):
        out = self.conv(x)
        out = self.bn(out)
        out = self.relu(out)
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.avg_pool(out)
        out = out.view(out.size(0), -1)
        out = self.fc(out)
        return out
    
model = ResNet(ResidualBlock, [2, 2, 2])

if torch.cuda.device_count() > 1:
  model = nn.DataParallel(model, device_ids=[0,1])

model.to(device)

# 定义损失和优化器
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# 更新学习率
def update_lr(optimizer, lr):    
    for param_group in optimizer.param_groups:
        param_group['lr'] = lr

# 训练模型
total_step = len(train_loader)
curr_lr = learning_rate
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)
        
        # 前向传递
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # 后向传播和优化
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        if (i+1) % 100 == 0:
            print ("Epoch [{}/{}], Step [{}/{}] Loss: {:.4f}"
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

    # 随着迭代过程继续，需要不断降低学习率，以防止在局部震荡
    if (epoch+1) % 20 == 0:
        curr_lr /= 3
        update_lr(optimizer, curr_lr)

# 测试模型
model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Accuracy of the model on the test images: {} %'.format(100 * correct / total))

# 保存模型参数
torch.save(model.state_dict(), 'resnet.ckpt')

最后测试集上准确率：87.14 %

代码解析：

个人配置：2个 1080TI 显卡，为了能够使用全部显卡并行运算，在使用model的时候需要再嵌套一层nn.DataParallel，后面的参数跟的是GPU的id，一般默认从0开始。