d2l中神经元网络的迭代器

最新推荐文章于 2025-02-27 20:39:06 发布

be_lxx1

最新推荐文章于 2025-02-27 20:39:06 发布

阅读量528

点赞数

文章标签： python

本文链接：https://blog.youkuaiyun.com/be_lxx1/article/details/128899319

版权

该代码定义了在Chapter3中训练神经网络模型的函数，包括一个训练循环和每个训练epoch的过程。训练过程中使用了Animator绘制损失和准确率图表，确保训练损失小于0.5，并且训练和测试准确率在0.7以上。训练函数使用了自定义或PyTorch内置的优化器以及损失函数。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater):
    """Train a model (defined in Chapter 3).

    Defined in :numref:`sec_softmax_scratch`"""
    animator = Animator(xlabel='epoch', xlim=[1, num_epochs], ylim=[0.3, 0.9],
                        legend=['train loss', 'train acc', 'test acc'])
    for epoch in range(num_epochs):
        train_metrics = train_epoch_ch3(net, train_iter, loss, updater)
        test_acc = evaluate_accuracy(net, test_iter)
        animator.add(epoch + 1, train_metrics + (test_acc,))
    train_loss, train_acc = train_metrics
    assert train_loss < 0.5, train_loss
    assert train_acc <= 1 and train_acc > 0.7, train_acc
    assert test_acc <= 1 and test_acc > 0.7, test_acc



def train_epoch_ch3(net, train_iter, loss, updater):
    """The training loop defined in Chapter 3.

    Defined in :numref:`sec_softmax_scratch`"""
    # Set the model to training mode
    if isinstance(net, torch.nn.Module):
        net.train()
    # Sum of training loss, sum of training accuracy, no. of examples
    metric = Accumulator(3)
    for X, y in train_iter:
        # Compute gradients and update parameters
        y_hat = net(X)
        l = loss(y_hat, y)
        if isinstance(updater, torch.optim.Optimizer):
            # Using PyTorch in-built optimizer & loss criterion
            updater.zero_grad()
            l.mean().backward()
            updater.step()
        else:
            # Using custom built optimizer & loss criterion
            l.sum().backward()
            updater(X.shape[0])
        metric.add(float(l.sum()), accuracy(y_hat, y), y.numel())
    # Return training loss and training accuracy
    return metric[0] / metric[2], metric[1] / metric[2]