softmax实现

import matplotlib.pyplot as plt
import torch
from IPython import display
from d2l import torch as d2lbatch_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cmpcmp = y_hat.type(y.dtype)==y#返回预测正确的aggravatereturn 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]*ndef 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0updater.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, fmtsdef 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] * nif 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_metricslr = 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()