深度学习(李沐)—————Softmax回归

此次测试发现老是发现缺包，后面发现装的位置不对。先看一下环境文件

发现自己的用户名是gluon ，所以应该在d21-zh文件目录下进cmd应该输入conda activate gluon

然后在各种pip install xxx。

 

 

 导入包

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

 读取数据集

batch_size = 256

train_iter,test_iter = d2l.load_data_fashion_mnist(batch_size)

展开每个图像，看作784向量。数据集有10个类别，则输出维度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，对所有矩阵求和

X = torch.tensor([[1.0,2.0,3.0],[4.0,5.0,6.0]])
X.sum(0,keepdim=True),X.sum(1,keepdim=True)#分别以维度0和1求和    6=【1，2，3】相加 15=【4，5，6】自己相加

实现softmax

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

将每个元素变成一个非负数。概率原理，每行总和为1

X = torch.normal(0,1,(2,5))
X_prob = softmax(X)
X_prob,X_prob.sum(1)

具体实现softmax

def net(X):
    return softmax(torch.matmul(X.reshape((-1,W.shape[0])),W)+b) #-1表示批量大小

常见一个数据y_hat,包含两个样本在3个类别的预测概率,使用y作为y_haht中概率大索引

y = torch.tensor([0,2]) #两个真实的标号
y_hat = torch.tensor([[0.1,0.3,0.6],[0.3,0.2,0.5]])
y_hat[[0,1],y] #0.1是y_hat[0]在[0.1,0.3,0.6]里第y[0]  0.5是y_hat[1]在[0.3,0.,0.5]里第y[2] 

实现交叉熵损失函数

#print(y_hat,y) y_hat是预测集  y是预测的预测集标号
#print(y_hat[range(len(y_hat)),y])
def cross_entropy(y_hat,y):
    return -torch.log(y_hat[range(len(y_hat)),y]) #y_hat[range(len(y_hat)),y]与上段测试相同
cross_entropy(y_hat,y)

将预测类别与真实y元素比较

def accuracy(y_hat,y):
    """计算正确预测的数量"""
    if len(y_hat.shape)>1 and y_hat.shape[1]>1: #判断y_hat是否为矩阵
        y_hat = y_hat.argmax(axis=1)
    cmp = y_hat.type(y.dtype) == y
    return float(cmp.type(y.dtype).sum())   #y是int类型 cmp转int求和再转float

accuracy(y_hat,y)/len(y) #测试结果

评估在任意模型net的准确率

def evaluate_accuracy(net, data_iter):  #@save
    """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 train_iter:
        metric.add(accuracy(net(X), y), y.numel())
    return metric[0] / metric[1]   #    metric[0]是分类正确   metric[1]是分类总数

Accumulator实例创建2个变量，分别存储正确预测数量和预测总数量

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)

Softmax回归训练

def train_epoch_ch3(net,train_iter,loss,updater):
    if isinstance(net,torch.nn.Module):
        net.train()
    metric = Accumulator(3)
    #for X,y in data_iter(batch_size,features,labels):此线性的
    for X,y in train_iter: #(batch_size,features,labels)在上文集合了
        #l = loss(net(X),y)
        y_hat = net(X)
        l = loss(y_hat,y)   #上下不可改为 l = loss(net(X),y)  因为y_hat类型是float
        if isinstance(updater,torch.optim.Optimizer):
            updater.zero_grad()
            l.backward()
            updater.step()
            metric.add(
            float(1)*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
    

小批量随机梯度下降优化模型店损失函数

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)

显示

 对图像进行分类预测

def predict_ch3(net, test_iter, n=6):  
    """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(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_ch3(net,test_iter)

显示