卷积神经网络¶

import torch
from torch import nn


# 为了方便起见，我们定义了一个计算卷积层的函数。
# 此函数初始化卷积层权重，并对输入和输出提高和缩减相应的维数
def comp_conv2d(conv2d, X):
    # 这里的（1，1）表示批量大小和通道数都是1
    X = X.reshape((1, 1) + X.shape)
    Y = conv2d(X)
    # 省略前两个维度：批量大小和通道
    return Y.reshape(Y.shape[2:])

# 请注意，这里每边都填充了1行或1列，因此总共添加了2行或2列
conv2d = nn.Conv2d(1, 1, kernel_size=3, padding=1)
X = torch.rand(size=(8, 8))
comp_conv2d(conv2d, X).shape

conv2d = nn.Conv2d(1, 1, kernel_size=(5, 3), padding=(2, 1))
comp_conv2d(conv2d, X).shape

conv2d = nn.Conv2d(1, 1, kernel_size=3, padding=1, stride=2)
comp_conv2d(conv2d, X).shape

conv2d = nn.Conv2d(1, 1, kernel_size=(3, 5), padding=(0, 1), stride=(3, 4))
comp_conv2d(conv2d, X).shape

import torch
from d2l import torch as d2l

def corr2d_multi_in(X, K):
    # 先遍历“X”和“K”的第0个维度（通道维度），再把它们加在一起
    return sum(d2l.corr2d(x, k) for x, k in zip(X, K))

X = torch.tensor([[[0.0, 1.0, 2.0], [3.0, 4.0, 5.0], [6.0, 7.0, 8.0]],
               [[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]]])
K = torch.tensor([[[0.0, 1.0], [2.0, 3.0]], [[1.0, 2.0], [3.0, 4.0]]])

corr2d_multi_in(X, K)
#output：
#tensor([[ 56.,  72.],
#        [104., 120.]])

def corr2d_multi_in_out(X, K):
    # 迭代“K”的第0个维度，每次都对输入“X”执行互相关运算。
    # 最后将所有结果都叠加在一起
    return torch.stack([corr2d_multi_in(X, k) for k in K], 0)

K = torch.stack((K, K + 1, K + 2), 0)
K.shape
#K从3个维度变成4个维度：输出是3，输入是2，宽高为2*2
#torch.Size([3, 2, 2, 2])
corr2d_multi_in_out(X, K)

#tensor([[[ 56.,  72.],
#         [104., 120.]],

#        [[ 76., 100.],
#         [148., 172.]],

#        [[ 96., 128.],
#         [192., 224.]]])

def corr2d_multi_in_out_1x1(X, K):
    c_i, h, w = X.shape
    c_o = K.shape[0]
    #变成c_i个大小为h*w的向量
    X = X.reshape((c_i, h * w))
    K = K.reshape((c_o, c_i))
    # 全连接层中的矩阵乘法
    Y = torch.matmul(K, X)
    return Y.reshape((c_o, h, w))

#验证
X = torch.normal(0, 1, (3, 3, 3))
K = torch.normal(0, 1, (2, 3, 1, 1))

Y1 = corr2d_multi_in_out_1x1(X, K)
Y2 = corr2d_multi_in_out(X, K)
assert float(torch.abs(Y1 - Y2).sum()) < 1e-6

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

net = nn.Sequential(
    #设置padding使得输入输出矩阵大小一致
    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(),
    nn.Linear(16 * 5 * 5, 120), nn.Sigmoid(),
    nn.Linear(120, 84), nn.Sigmoid(),
    nn.Linear(84, 10))

def evaluate_accuracy_gpu(net, data_iter, device=None): #@save
    """使用GPU计算模型在数据集上的精度"""
    if isinstance(net, nn.Module):
        net.eval()  # 设置为评估模式
        if not device:
            device = next(iter(net.parameters())).device
    # 正确预测的数量，总预测的数量
    metric = d2l.Accumulator(2)
    with torch.no_grad():
        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]
            else:
                X = X.to(device)
            y = y.to(device)
            metric.add(d2l.accuracy(net(X), y), y.numel())
    return metric[0] / metric[1]

#@save
def train_ch6(net, train_iter, test_iter, num_epochs, lr, device):
    """用GPU训练模型(在第六章定义)"""
    def init_weights(m):
        if type(m) == nn.Linear or type(m) == nn.Conv2d:
            nn.init.xavier_uniform_(m.weight)
    #用xavier初始化权重
    net.apply(init_weights)
    print('training on', device)
    net.to(device)
    optimizer = torch.optim.SGD(net.parameters(), lr=lr)
    loss = nn.CrossEntropyLoss()
    #设置动画效果(打印信息)
    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))
        #打印信息
        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)}')