softmax 回归实现

代码部分

引入Fashion-MNIST数据集

import tensorflow as tf
from IPython import display
from d2l import tensorflow as d2l

设置数据批量大小

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

初始化模型参数

num_inputs = 784
num_outputs = 10

W = tf.Variable(tf.random.normal(shape=(num_inputs, num_outputs),
                                 mean=0, stddev=0.01))
b = tf.Variable(tf.zeros(num_outputs))

定义softmax操作

测试加法操作

X = tf.constant([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
tf.reduce_sum(X, 0, keepdims=True), tf.reduce_sum(X, 1, keepdims=True)

定义softmax函数

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

X = tf.random.normal((2, 5), 0, 1)
X_prob = softmax(X)
X_prob, tf.reduce_sum(X_prob, 1)
out:
(<tf.Tensor: shape=(2, 5), dtype=float32, numpy=
 array([[0.0316517 , 0.07830442, 0.31889546, 0.04518747, 0.52596086],
        [0.05555104, 0.3102902 , 0.1781524 , 0.2898441 , 0.16616222]],
       dtype=float32)>,
 <tf.Tensor: shape=(2,), dtype=float32, numpy=array([0.9999999, 1.       ], dtype=float32)>)

定义模型

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

定义损失函数

y_hat = tf.constant([[0.1, 0.3, 0.6], [0.3, 0.2, 0.5]])
y = tf.constant([0, 2])
tf.boolean_mask(y_hat, tf.one_hot(y, depth=y_hat.shape[-1]))

def cross_entropy(y_hat, y):
    return -tf.math.log(tf.boolean_mask(
        y_hat, tf.one_hot(y, depth=y_hat.shape[-1])))

cross_entropy(y_hat, y)

分类精度

def accuracy(y_hat, y):  #@save
    """计算预测正确的数量"""
    if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
        y_hat = tf.argmax(y_hat, axis=1)
    cmp = tf.cast(y_hat, y.dtype) == y
    return float(tf.reduce_sum(tf.cast(cmp, y.dtype)))

def evaluate_accuracy(net, data_iter):  #@save
    """计算在指定数据集上模型的精度"""
    metric = Accumulator(2)  # 正确预测数、预测总数
    for X, y in data_iter:
        metric.add(accuracy(net(X), y), d2l.size(y))
    return metric[0] / metric[1]

class Accumulator:  #@save
    """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]

evaluate_accuracy(net, test_iter)

训练

def train_epoch_ch3(net, train_iter, loss, updater):  #@save
    """训练模型一个迭代周期（定义见第3章）"""
    # 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
        with tf.GradientTape() as tape:
            y_hat = net(X)
            # Keras内置的损失接受的是（标签，预测），这不同于用户在本书中的实现。
            # 本书的实现接受（预测，标签），例如我们上面实现的“交叉熵”
            if isinstance(loss, tf.keras.losses.Loss):
                l = loss(y, y_hat)
            else:
                l = loss(y_hat, y)
        if isinstance(updater, tf.keras.optimizers.Optimizer):
            params = net.trainable_variables
            grads = tape.gradient(l, params)
            updater.apply_gradients(zip(grads, params))
        else:
            updater(X.shape[0], tape.gradient(l, updater.params))
        # Keras的loss默认返回一个批量的平均损失
        l_sum = l * float(tf.size(y)) if isinstance(
            loss, tf.keras.losses.Loss) else tf.reduce_sum(l)
        metric.add(l_sum, accuracy(y_hat, y), tf.size(y))
    # 返回训练损失和训练精度
    return metric[0] / metric[2], metric[1] / metric[2]

class Animator:  #@save
    """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):  #@save
    """训练模型（定义见第3章）"""
    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

小批量随机梯度下降来优化模型的损失函数

class Updater():  #@save
    """用小批量随机梯度下降法更新参数"""
    def __init__(self, params, lr):
        self.params = params
        self.lr = lr

    def __call__(self, batch_size, grads):
        d2l.sgd(self.params, grads, self.lr, batch_size)

updater = Updater([W, b], lr=0.1)

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)

预测
现在训练已经完成，我们的模型已经准备好[对图像进行分类预测]。 给定一系列图像，我们将比较它们的实际标签（文本输出的第一行）和模型预测（文本输出的第二行）。

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

predict_ch3(net, test_iter)

小结

• 借助softmax回归，我们可以训练多分类的模型。
• 训练softmax回归循环模型与训练线性回归模型非常相似：先读取数据，再定义模型和损失函数，然后使用优化算法训练模型。大多数常见的深度学习模型都有类似的训练过程。