3.6

def accuracy(y_hat, y): #@save

def accuracy(y_hat, y):
    """计算预测正确的数量
    Defined in :numref:`sec_softmax_scratch`"""
    if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
        y_hat = d2l.argmax(y_hat, axis=1)
    cmp = d2l.astype(y_hat, y.dtype) == y
    return float(d2l.reduce_sum(d2l.astype(cmp, y.dtype)))

class Accumulator: #@save

class Accumulator:
    """在n个变量上累加"""
    def __init__(self, n):
        """Defined in :numref:`sec_softmax_scratch`"""
        self.data = [0.0] * n

    def add(self, *args):
        self.data = [a + float(b) for a, b in zip(self.data, args)]

    def reset(self):
        self.data = [0.0] * len(self.data)

    def __getitem__(self, idx):
        return self.data[idx]

def evaluate_accuracy(net, data_iter): #@save

def evaluate_accuracy(net, data_iter):
    """计算在指定数据集上模型的精度
    Defined in :numref:`sec_softmax_scratch`"""
    if isinstance(net, torch.nn.Module):
        net.eval()  # 将模型设置为评估模式
    metric = Accumulator(2)  # 正确预测数、预测总数
    with torch.no_grad():
        for X, y in data_iter:
            metric.add(accuracy(net(X), y), d2l.size(y))
    return metric[0] / metric[1]

def train_epoch_ch3(net, train_iter, loss, updater): #@save

def train_epoch_ch3(net, train_iter, loss, updater):
    """训练模型一个迭代周期（定义见第3章）
    Defined in :numref:`sec_softmax_scratch`"""
    # 将模型设置为训练模式
    if isinstance(net, torch.nn.Module):
        net.train()
    # 训练损失总和、训练准确度总和、样本数
    metric = Accumulator(3)
    for X, y in train_iter:
        # 计算梯度并更新参数
        y_hat = net(X)
        l = loss(y_hat, y)
        if isinstance(updater, torch.optim.Optimizer):
            # 使用PyTorch内置的优化器和损失函数
            updater.zero_grad()
            l.mean().backward()
            updater.step()
        else:
            # 使用定制的优化器和损失函数
            l.sum().backward()
            updater(X.shape[0])
        metric.add(float(l.sum()), accuracy(y_hat, y), y.numel())
    # 返回训练损失和训练精度
    return metric[0] / metric[2], metric[1] / metric[2]

class Animator: #@save

class Animator:
    """在动画中绘制数据"""
    def __init__(self, xlabel=None, ylabel=None, legend=None, xlim=None,
                 ylim=None, xscale='linear', yscale='linear',
                 fmts=('-', 'm--', 'g-.', 'r:'), nrows=1, ncols=1,
                 figsize=(3.5, 2.5)):
        """Defined in :numref:`sec_softmax_scratch`"""
        # 增量地绘制多条线
        if legend is None:
            legend = []
        d2l.use_svg_display()
        self.fig, self.axes = d2l.plt.subplots(nrows, ncols, figsize=figsize)
        if nrows * ncols == 1:
            self.axes = [self.axes, ]
        # 使用lambda函数捕获参数
        self.config_axes = lambda: d2l.set_axes(
            self.axes[0], xlabel, ylabel, xlim, ylim, xscale, yscale, legend)
        self.X, self.Y, self.fmts = None, None, fmts

    def add(self, x, y):
        # 向图表中添加多个数据点
        if not hasattr(y, "__len__"):
            y = [y]
        n = len(y)
        if not hasattr(x, "__len__"):
            x = [x] * n
        if not self.X:
            self.X = [[] for _ in range(n)]
        if not self.Y:
            self.Y = [[] for _ in range(n)]
        for i, (a, b) in enumerate(zip(x, y)):
            if a is not None and b is not None:
                self.X[i].append(a)
                self.Y[i].append(b)
        self.axes[0].cla()
        for x, y, fmt in zip(self.X, self.Y, self.fmts):
            self.axes[0].plot(x, y, fmt)
        self.config_axes()
        display.display(self.fig)
        display.clear_output(wait=True)

def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater): #@save

def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater):
    """训练模型（定义见第3章）
    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 predict_ch3(net, test_iter, n=6): #@save

def predict_ch3(net, test_iter, n=6):
    """预测标签（定义见第3章）
    Defined in :numref:`sec_softmax_scratch`"""
    for X, y in test_iter:
        break
    trues = d2l.get_fashion_mnist_labels(y)
    preds = d2l.get_fashion_mnist_labels(d2l.argmax(net(X), axis=1))
    titles = [true +'\n' + pred for true, pred in zip(trues, preds)]
    d2l.show_images(
        d2l.reshape(X[0:n], (n, 28, 28)), 1, n, titles=titles[0:n])

from d2l import torch as d2l
import torch

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

num_inputs = 784
num_outputs = 10

W = torch.normal(0, 0.01, size=(num_inputs, num_outputs), requires_grad=True)
b = torch.zeros(num_outputs, requires_grad=True)

def softmax(X):
    X_exp = torch.exp(X)
    partition = X_exp.sum(1, keepdim=True)
    return X_exp / partition  # 这里应用了广播机制

def net(X):
    return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b)

def cross_entropy(y_hat, y):
    return - torch.log(y_hat[range(len(y_hat)), y])

lr = 0.1
def updater(batch_size):
    return d2l.sgd([W, b], lr, batch_size)

num_epochs = 10
d2l.train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, updater)

d2l.predict_ch3(net, test_iter, 8)

3.7

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

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

net = nn.Sequential(nn.Flatten(), nn.Linear(784, 10))
loss = nn.CrossEntropyLoss(reduction='none')
trainer = torch.optim.SGD(net.parameters(), lr=0.1)

def init_weights(m):
    if type(m) == nn.Linear:
        nn.init.normal_(m.weight, std=0.01)

net.apply(init_weights)

num_epochs = 10
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)

d2l.predict_ch3(net, test_iter, 8)

net[1].weight.shape
net[1].bias

4.2

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

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

num_inputs = 784
num_outputs = 10
num_hiddens = 256

W1 = nn.Parameter(torch.randn(num_inputs, num_hiddens, requires_grad=True) * 0.01)
b1 = nn.Parameter(torch.zeros(num_hiddens, requires_grad=True))
W2 = nn.Parameter(torch.randn(num_hiddens, num_outputs, requires_grad=True) * 0.01)
b2 = nn.Parameter(torch.zeros(num_outputs, requires_grad=True))
params = [W1, b1, W2, b2]

def relu(X):
    a = torch.zeros_like(X)
    return torch.max(X, a)

def net(X):
    X = X.reshape((-1, num_inputs))
    H = relu(X@W1 + b1)  # 这里“@”代表矩阵乘法
    return (H@W2 + b2)

loss = nn.CrossEntropyLoss(reduction='none')

lr = 0.1
updater = torch.optim.SGD(params, lr=lr)

num_epochs = 10
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, updater)

d2l.predict_ch3(net, test_iter, 8)
print(params[0].shape, params[1].shape, params[2].shape, params[3].shape)

4.3

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

batch_size = 256
lr = 0.1
num_epochs = 10

train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

net = nn.Sequential(nn.Flatten(), nn.Linear(784, 256), nn.ReLU(), nn.Linear(256, 10))
loss = nn.CrossEntropyLoss(reduction='none')
trainer = torch.optim.SGD(net.parameters(), lr=lr)

def init_weights(m):
    if type(m) == nn.Linear:
        nn.init.normal_(m.weight, std=0.01)

net.apply(init_weights)

d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)

d2l.predict_ch3(net, test_iter, 8)

print(net[1].weight.shape, net[1].bias.shape, net[3].weight.shape, net[3].bias.shape)