softmax实现

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

batch_size = 256
train_iter,test_iter = d2l.load_data_fashion_mnist(batch_size)
test_iter.num_workers = 0
train_iter.num_workers = 0
num_inputs = 784   # 将图片数据拉伸成一个向量  28*28=784
num_outputs = 10   # 类别数量

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   # 使用了广播机制 使得矩阵所有元素均大于0，且可解释为概率
# 验证softmax
x = torch.normal(0,1,(2,5))
x_prob = softmax(x)
x_prob,x_prob.sum(1)
# 实现softmax回归模型,得到可解释为概率的张量
def net(x):
#     x.reshape为268*784的矩阵
    return softmax(torch.matmul(x.reshape((-1,w.shape[0])),w)+b)
# 拿出预测索引,其中包含两个样本在三个类别的预测
y = torch.tensor([0,2])
y_hat = torch.tensor([[0.1,0.3,0.6],[0.3,0.2,0.5]])

y_hat[[0,1],y]

"""[0，1]指的是真实样本的下标，对于第0个样本，拿出y[0]样本类别的预测值，
对于第1个样本，拿出y[1]样本类别的预测值。拿出真实标号类的预测值。"""

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

cross_entropy(y_hat,y)
# 比较预测值和真实y
def accuracy(y_hat,y):
    if len(y_hat.shape)>1 and y_hat.shape[1]>1:
        # 元素最大的那个下表存到y_hat里面
        y_hat = y_hat.argmax(axis=1)
    #把y_hat转为y的数据类型再与y做比较，存入cmp
    cmp = y_hat.type(y.dtype)==y
    #返回预测正确的aggravate
    return float(cmp.type(y.dtype).sum())
accuracy(y_hat,y)/len(y)
def evaluate_accuracy(net,data_iter):
    """计算指定数据集上的精度"""
    if isinstance(net,torch.nn.Module):
        """将模型设置为评估模式"""
        net.eval()
        """正确预测数，预测总数"""
    metric = Accumulator(2)
    for x,y in data_iter:
        metric.add(accuracy(net(x),y),y.numel())
    return metric[0] / metric[1]
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]

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()
    """长度为3的迭代器来累加信息"""
    metric = Accumulator(3)
    for x,y in train_iter:
        y_hat = net(x)
        l = loss(y_hat,y)
        if isinstance(updater,torch.optim.Optimizer):
#     梯度置0
            updater.zero_grad()
#     计算梯度
            l.backward()
#     更新参数
            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())
#      返回的是损失，所有loss的累加除以样本总数，  分类正确是样本数除以样本总数
    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()
        d2l.plt.draw()
        d2l.plt.pause(0.001)
        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):
    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

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)
d2l.plt.show()

一开始不出图，后来 再add函数中加

d2l.plt.draw()
d2l.plt.pause(0.001)

最后加d2l.plt.show()

参考