Softmax函数

import torch
from IPython import display
from d2l import torch as d2l
import matplotlib.pyplot as plt
import os

os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"

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

# 将展平每个图像，将它们视为长度为784的向量。因为我们的数据集有10个类别，所以网络输出维度为10
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)

# 给定一个矩阵X，我们可以对所有元素求和
X = torch.tensor([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
print(X.sum(0, keepdim=True))
print(X.sum(1, keepdim=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


# 我们将每个元素变成一个非负数，此外，依据概率原理，每行总和为1
X = torch.normal(0, 1, (2, 5))
X_prob = softmax(X)
print(X_prob)
print(X_prob.sum(1))


# 实现Softmax回归模型
def net(X):
    return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b)


# 创建一个数据y_hat，其中包含2个样本和3个类别的预测概率，使用y作为y_hat中概率的索引
y = torch.tensor([0, 2])
y_hat = torch.tensor([[0.1, 0.3, 0.6], [0.3, 0.2, 0.5]])
print(y_hat[[0, 1], y])
#第一个列表对应行数索引
#第二个列表对应列数索引


# 实现交叉熵损失函数
def cross_entropy(y_hat, y):
    return -torch.log(y_hat[range(len(y_hat)), y])


print(cross_entropy(y_hat, y))


# 将预测类别与真实y元素进行比较
def accuracy(y_hat, y):
    '''计算预测正确的数量'''
    if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
        y_hat = y_hat.argmax(axis=1)
    cmp = y_hat.type(y.dtype) == y
    return float(cmp.type(y.dtype).sum())


accuracy(y_hat, y) / len(y)


# Accumulator实例中创建了2个变量，用于分别存储正确预测的数量和预测的总数量
class Accumulator:
    '''在n个变量上累加'''

    def __init__(self, n):
        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]


# 我们可以评估在任意模型net的准确率
def evaluate_accuracy(net, data_iter):
    '''计算在指定数据集上模型的精度'''
    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
    for X, y in data_iter:
        metric.add(accuracy(net(X), y), y.numel())
    return metric[0] / metric[1]


# Softmax回归的训练
def train_epoch_ch3(net, train_iter, loss, updater):
    if isinstance(net, torch.nn.Module):
        net.train()
    metric = Accumulator(3)
    for X, y in train_iter:
        y_hat = net(X)
        l = loss(y_hat, y)
        if isinstance(updater, torch.optim.Optimizer):
            updater.zero_grad()
            l.backward()
            updater.step()
            metric.add(
                float(l) * len(y), accuracy(y_hat, y), y.size().numel())
        else:
            l.sum().backward()
            updater(X.shape[0])
            metric.add(float(l.sum()), accuracy(y_hat, y), y.numel())
    return metric[0] / metric[2], metric[1] / metric[2]


# 定义一个在动画中绘制数据的实用程序类
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)):
        # 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)


# 训练函数
def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater):
    '''训练模型'''
    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 1 >= train_acc > 0.7, train_acc
    assert 1 >= test_acc > 0.7, test_acc
    plt.show()


lr = 0.1


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


# 训练模型10个迭代周期
num_epochs = 10
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, updater)


# 对图像进行分类预测
def predict_ch3(net, test_iter, n=6):
    '''预测标签'''
    for X, y in test_iter:
        break
    trues = d2l.get_fashion_mnist_labels(y)
    preds = d2l.get_fashion_mnist_labels(net(X).argmax(axis=1))
    titles = [true + '\n' + pred for true, pred in zip(trues, preds)]
    d2l.show_images(
        X[0:n].reshape((n, 28, 28)), 1, n, titles=titles[0:n]
    )
    plt.show()


predict_ch3(net, test_iter)

简洁实现

# 通过深度学习框架的高级API能够使实现softmax回归变得更加容易
import torch
from torch import nn
from d2l import torch as d2l
import os
import matplotlib.pyplot as plt

os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"

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

# Softmax回归的输出层是一个全连接层
# PyTorch不会隐式地调整输入的形状
# 因此，我们定义了展平层（flatten）在线性层前调整网络输入的形状
net = nn.Sequential(nn.Flatten(), nn.Linear(784, 10))


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


net.apply(init_weights)

# 在交叉熵损失函数中传递未归一化的预测，并同时计算softmax及其对数
loss = nn.CrossEntropyLoss()

# 使用学习率为0.1的小批量随机梯度下降作为优化算法
trainer = torch.optim.SGD(net.parameters(), lr=0.1)

# 调用之前定义的训练函数来训练模型
num_epochs = 100
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)
plt.show()