【pytorch版】softmax回归的从零开始实现

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)

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)

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)

def softmax(X):
    X_exp = torch.exp(X)
    partition = X_exp.sum(1, keepdims=True)
    return X_exp / partition
X=torch.normal(0,1,(2,5))
X_prob=softmax(X)
X_prob,X_prob.sum(1)

#实现softmax回归模型
def net(X):
    return softmax(torch.matmul(X.reshape((-1,w.shape[0])),w)+b)

#创建一个数据y_ hat， 其中包含2个样本在3个类别的预测概率，使用 y作为y_ hat中概率的索引

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]

#定义交叉熵函数
def cross_entropy(y_hat,y):
    return -torch.log(y_hat[range(len(y_hat)),y])
cross_entropy(y_hat,y)

#将预测类别与真实y元素进行比较
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)#每一行中元素最大的下标
    cmp=y_hat.type(y.dtype)==y
    return float(cmp.type(y.dtype).sum())
accuracy(y_hat,y)/len(y)

#可以评估在任意模型net的准确率
def evaluate_accuracy(net, data_iter):
    """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 data_iter :
            metric.add(accuracy(net(X),y),y.numel())
            return metric[0] / metric[1]

#Accumulator实例中创建了2个变量，用于分别存储正确预测的数量和预测的总数量
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)

def train_epoch_ch3(net,train_iter,loss,updater):
    if isinstance (net,torch.nn.Module):
        net.train()
    metric = Accumulator(3)
    for X,y in train_iter:
        y_hat = net(X)
        l = loss(y_hat, y)
        if isinstance (updater, torch.optim.optimizer):
            updater.zero_grad()
            l.backward()
            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())
        return metric[0] / metric[2],metric[1] / metric[2]

#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],
                         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 

num_epochs=10
train_ch3(net,train_iter,test_iter,cross_entropy,num_epochs,updater=True)