介绍

Pytorch Linghtning 是在 pytorch 基础上进行封装的库，为了让用户专注于核心代码的构建，提供许多的实用工具，可以让实验更加高效。

Lightning

lightning 大致分为三个部分：

• 研究代码（LightningModule），主要是模型的结构、训练等部分，
• 工程代码（Trainer），代码重复性高的部分，比如分布式训练，
• 非必要代码（Callbacks），没有直接的关系，起辅助的作用，比如梯度检查，log 输出等。

LightningModule 组件

• 模型
• 数据处理
• 损失函数
• 优化器

步骤

1. 初始化，__ init __()
2. 准备数据
3. 配置优化器
4. 配置测试部分
5. 加载数据
6. 训练

示例

pytorch 版本

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, 3, 1)
        self.conv2 = nn.Conv2d(32, 64, 3, 1)
        self.dropout1 = nn.Dropout(0.25)
        self.dropout2 = nn.Dropout(0.5)
        self.fc1 = nn.Linear(9216, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = F.relu(x)
        x = self.conv2(x)
        x = F.relu(x)
        x = F.max_pool2d(x, 2)
        x = self.dropout1(x)
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.dropout2(x)
        x = self.fc2(x)
        output = F.log_softmax(x, dim=1)
        return output

训练测试部分

def train(args, model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % args.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()))
            if args.dry_run:
                break

def test(model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction='sum').item()  # sum up batch loss
            pred = output.argmax(dim=1, keepdim=True)  # get the index of the max log-probability
            correct += pred.eq(target.view_as(pred)).sum().item()

    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)))

Lightning 版本

class LitClassifier(pl.LightningModule):
    def __init__(self, hidden_dim=128, learning_rate=1e-3):
        super().__init__()
        self.save_hyperparameters()

        self.l1 = torch.nn.Linear(28 * 28, self.hparams.hidden_dim)
        self.l2 = torch.nn.Linear(self.hparams.hidden_dim, 10)

    def forward(self, x):
        x = x.view(x.size(0), -1)
        x = torch.relu(self.l1(x))
        x = torch.relu(self.l2(x))
        return x

    def training_step(self, batch, batch_idx):
        x, y = batch
        y_hat = self(x)
        loss = F.cross_entropy(y_hat, y)
        return loss

    def validation_step(self, batch, batch_idx): # 验证部分
        x, y = batch
        y_hat = self(x)
        loss = F.cross_entropy(y_hat, y)
        self.log('valid_loss', loss)

    def test_step(self, batch, batch_idx):
        x, y = batch
        y_hat = self(x)
        loss = F.cross_entropy(y_hat, y)
        self.log('test_loss', loss)

    def configure_optimizers(self):
        return torch.optim.Adam(self.parameters(), lr=self.hparams.learning_rate)

    @staticmethod  # 声明一个静态方法
    def add_model_specific_args(parent_parser):
        parser = ArgumentParser(parents=[parent_parser], add_help=False)
        parser.add_argument('--hidden_dim', type=int, default=128)
        parser.add_argument('--learning_rate', type=float, default=0.0001)
        return parser

def cli_main():
    pl.seed_everything(1234) # 这个是用于固定 seed 用

    # args
    parser = ArgumentParser()
    parser = pl.Trainer.add_argparse_args(parser)
    parser = LitClassifier.add_model_specific_args(parser)
    parser = MNISTDataModule.add_argparse_args(parser)
    args = parser.parse_args()

    # data
    dm = MNISTDataModule.from_argparse_args(args)

    # model
    model = LitClassifier(args.hidden_dim, args.learning_rate)

    # training
    trainer = pl.Trainer.from_argparse_args(args)
    trainer.fit(model, datamodule=dm)

    result = trainer.test(model, datamodule=dm)
    print(result)