李沐动手学深度学习：softmax回归的从零开始实现

import torch
from IPython import display
from d2l import torch as d2l

batach_size=256
train_iter,test_iter = d2l.load_data_fashion_mnist(batach_size)
num_input = 784 #图片的尺寸：28*28
num_output = 10 #10个类别
W = torch.normal(0,0.01,size=(num_input,num_output),requires_grad=True)
b = torch.zeros(num_output,requires_grad=True)

def softmax(X):
    X_exp = torch.exp(X)
    partition = X_exp.sum(1,keepdim=True)
    return X_exp/partition

#定义模型
def net(X):
    return softmax(torch.matmul(X.reshape((-1,W.shape[0])),W)+b)
    
#交叉熵损失
def cross_entropy(y_hat,y):
    return -torch.log(y_hat[range(len(y_hat)),y])

#使⽤argmax获得每⾏中最⼤元素的索引来获得预测类别
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)
    #由于等式运算符“==”对数据类型很敏感，因此我们将y_hat的数据类型转换为与y的数据类型⼀致
    cmp = y_hat.type(y.dtype) == y
    return float(cmp.type(y.dtype).sum())

class Accumulator:
    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]

def evaluate_accuracy(net,data_iter):
    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),y.numel())
    return metric[0]/metric[1]

#训练
def train_epoch(net,train_iter,loss,updater):
    if isinstance(net, torch.nn.Module):
        net.train()
    #训练损失总合、训练准确度总和、样本数
    metric = Accumulator(3)
    for X,y in train_iter:
        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.setp()
        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
    """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)

def train(net,train_iter,test_iter,loss,num_epoch,updater):
    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(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

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

num_epochs = 10
train(net, train_iter, test_iter, cross_entropy, num_epochs, updater)

#预测
def predict(net,test_iter,n=6):
    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])

predict(net,test_iter)
   

训练图像

测试