22-lenet网络

import torch
import torch.nn as nn
from d2l import torch as d2l

net = nn.Sequential(nn.Conv2d(1, 6, kernel_size=(5, 5), padding=2),
                    nn.Sigmoid(),
                    nn.AvgPool2d(kernel_size=(2, 2), stride=2),
                    nn.Conv2d(6, 16, kernel_size=(5, 5)),
                    nn.Sigmoid(),
                    nn.AvgPool2d(kernel_size=(2, 2), stride=2),
                    nn.Flatten(),
                    nn.Linear(16*5*5, 120),
                    nn.Sigmoid(),
                    nn.Linear(120, 84),
                    nn.Sigmoid(),
                    nn.Linear(84, 10))

X = torch.rand(size=(1, 1, 28, 28), dtype=torch.float32)
for layer in net:
    X = layer(X)
    print(layer.__class__.__name__, '------', X.shape)

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

# 估计模型的准确率
def evaluate_accuracy_gpu(net, data_iter, device = None):
    if isinstance(net, nn.Module):
        net.eval() # 停止dropout和梯度计算
        if device is None:
            device = next(iter(net.parameters())).device
    metric = d2l.Accumulator(2) # 0：正确预测的数量 1：总预测数量
    with torch.no_grad():
        for X, y in data_iter:
            if isinstance(X, list):
                X = [x.to(device) for x in X]
            else:
                X = X.to(device)
            y = y.to(device)
            metric.add(d2l.accuracy(net(X), y), y.numel()) # numel获取一共多少元素
    return metric[0] / metric[1]


def train(net, train_iter, test_iter, num_epochs, lr, device):
    # 参数初始化
    def init_weights(m):
        if isinstance(m, nn.Linear) or isinstance(m, nn.Conv2d):
            nn.init.xavier_uniform_(m.weight)

    net.apply(init_weights)
    net.to(device)

    # 定义损失函数和优化器
    optimizer = torch.optim.SGD(net.parameters(), lr=lr)
    loss = nn.CrossEntropyLoss()

    animator = d2l.Animator(xlabel='epoch', xlim=[1, num_epochs],
                            legend=['train loss', 'train acc', 'test acc'])
    timer, num_batches = d2l.Timer(), len(train_iter)

    for epoch in range(num_epochs):
        # 训练损失之和，训练准确率之和，样本数
        metric = d2l.Accumulator(3)
        net.train() # 开启训练模式
        for i, (X, y) in enumerate(train_iter):
            timer.start()
            X = X.to(device)
            y = y.to(device)
            optimizer.zero_grad()
            y_pred = net(X)
            l = loss(y_pred, y)
            l.backward()
            optimizer.step()
            with torch.no_grad():
                metric.add(l * X.shape[0], d2l.accuracy(y_pred, y), X.shape[0])
            timer.stop()
            train_l = metric[0] / metric[2]
            train_acc = metric[1] / metric[2]
            if (i + 1) % (num_batches // 5) == 0 or i == num_batches - 1:
                animator.add(epoch + (i + 1) / num_batches,
                             (train_l, train_acc, None))
        test_acc = evaluate_accuracy_gpu(net, test_iter)
        animator.add(epoch + 1, (None, None, test_acc))
    print(f'loss {train_l:.3f}, train acc {train_acc:.3f}, '
          f'test acc {test_acc:.3f}')
    print(f'{metric[2] * num_epochs / timer.sum():.1f} examples/sec '
          f'on {str(device)}')


lr, num_epochs = 0.1, 10
train(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())