论文要点：LeNet（模型M+公式F+代码C）

# LeNet

论文：Gradient-Based Learning Applied to Document Recognition by YANN LECUN, et al

1. 模型：

2. 代码：

# 代码来自动手学深度学习 by 李沐
import torch
from torch import nn
from d2l import torch as d2l

net = nn.Sequential(nn.Conv2d(1, 6, kernel_size=5, padding=2), 
                    nn.Sigmoid(), 
                    nn.AvgPool2d(2, stride=2), 
                    nn.Conv2d(6, 16, kernel_size=5),
                    nn.Sigmoid(), 
                    nn.AvgPool2d(2, stride=2),
                    nn.Flatten(), 
                    nn.Linear(400, 120), 
                    nn.Sigmoid(),
                    nn.Linear(120, 84), 
                    nn.Sigmoid(), 
                    nn.Linear(84, 10))

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

def evaluate_accuracy_gpu(net, data_iter, device=None):
    """使用GPU计算模型在数据集上的精度"""
    if isinstance(net, torch.nn.Module):
        net.eval()
        if not device:
            device = next(iter(net.parameters())).device  #查看parameter第一组的device存在哪里
    metric = d2l.Accumulator(2)  #做一个累加器
    with torch.no_grad():
        for X, y in data_iter:
            if isinstance(X, list):
                X = [x.to(device) for x in X]  #如果是list就逐个放入
            else:
                X = X.to(device)  #如果是tensor就一次放入
            y = y.to(device)
            metric.add(d2l.accuracy(net(X), y), y.numel())
    return metric[0] / metric[1]

def train_ch6(net, train_iter, test_iter, num_epochs, lr, device):
    """train a model with a GPU"""
    def init_weights(m):
        if type(m) == nn.Linear or type(m) == nn.Conv2d:
            nn.init.xavier_normal_(m.weight)
    net.apply(init_weights)
    print('training on ', device)
    net.to(device)
    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):
        metric = d2l.Accumulator(3)
        net.train()
        for i, (X, y) in enumerate(train_iter):
            timer.start()
            optimizer.zero_grad()
            X, y = X.to(device), y.to(device)
            y_hat = net(X)
            l = loss(y_hat, y)
            l.backward()
            optimizer.step()
            with torch.no_grad():
                metric.add(l * X.shape[0], d2l.accuracy(y_hat, y), X.shape[0])
            timer.stop()
            train_1 = 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_1, train_acc, None))
        test_acc = evaluate_accuracy_gpu(net, test_iter)
        animator.add(epoch + 1, (None, None, test_acc))
        print(f'loss {train_1:.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 = 0.3, 30
train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())