23 经典卷积神经网络 LeNet（pycharm版）

import torch
from torch import nn
from d2l import torch as d2l
import os
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"

# 23 经典卷积神经网络 LeNet
net = nn.Sequential(
    nn.Conv2d(1, 6, kernel_size=5, padding=2), nn.Sigmoid(),
    nn.AvgPool2d(kernel_size=2, stride=2),
    nn.Conv2d(6, 16, kernel_size=5), nn.Sigmoid(),
    nn.AvgPool2d(kernel_size=2, stride=2),
    nn.Flatten(),  # 将特征图（二维数组）展平为一维数组，为全连接层做准备
    nn.Linear(16 * 5 * 5, 120), nn.Sigmoid(),  # 全连接层
    nn.Linear(120, 84), nn.Sigmoid(),
    nn.Linear(84, 10))
# 检查模型
X = torch.rand(size=(1, 1, 28, 28), dtype=torch.float32)
for layer in net:
    X = layer(X)
    print(layer.__class__.__name__, 'output shape:\t', X.shape)

# 模型训练
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):  # net（模型），data_iter（数据迭代器），以及可选参数 device（用于指定设备，如GPU）
    """使用GPU计算模型在数据集上的精度"""
    if isinstance(net, nn.Module):  # 检查传入的模型 net 是否为 nn.Module 的实例
        net.eval()  # 设置为评估模式
        """如果是，则将模型设置为评估模式，
        这会关闭诸如dropout和batch normalization等模块的特定特性，
        这些特性在训练阶段使用，但在评估阶段不需要。"""
        if not device:
            device = next(iter(net.parameters())).device  # 获取模型参数中第一个元素的设备，以此作为默认的 device
    # 正确预测的数量，总预测的数量
    metric = d2l.Accumulator(2)  # 用于累加正确预测的样本数量和总预测的样本数量
    with torch.no_grad():  # torch.no_grad() 告诉PyTorch不计算梯度，这通常会在评估模式下使用，以减少计算量
        for X, y in data_iter:
            if isinstance(X, list):
                # BERT微调所需的（之后将介绍）
                X = [x.to(device) for x in X]  # 如果X是一个List，则把每个元素都移到device上
            else:
                X = X.to(device)  # 如果X是tensor，则只用移动一次，把X直接移到device上
            y = y.to(device)
            metric.add(d2l.accuracy(net(X), y), d2l.size(y))
    return metric[0] / metric[1]  # 最终返回正确预测数量除以总预测数量的比值，即准确度


# 训练函数
def train_ch6(net, train_iter, test_iter, num_epochs, lr, device):
    """用GPU训练模型"""
    def init_weights(m):
        if type(m) == nn.Linear or type(m) == nn.Conv2d:
            nn.init.xavier_uniform_(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):
        # 训练损失之和，训练准确率之和，样本数
        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_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)}')


# 训练和评估lenet模型
lr, num_epochs = 0.9, 10
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())
d2l.plt.show()  # 完全跑完后，可视化的图突然消失,加一句这个