【动手学深度学习笔记】之PyTorch实现多层感知机

import torchfrom torch import nnimport numpy as npimport syssys.path.append("..")
import torchvisionfrom IPython import displayfrom time import timeimport matplotlib.pyplot as pltimport torchvision.transforms as transformsfrom time import time

batch_size = 256
mnist_train = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST',train=True,download=True,transform=transforms.ToTensor())#获取训练集mnist_test = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST',train=False,download=True,transform=transforms.ToTensor())#获取测试集
#生成迭代器train_iter = torch.utils.data.DataLoader(mnist_train,batch_size=batch_size,shuffle = True,num_workers = 0)
test_iter = torch.utils.data.DataLoader(mnist_test,batch_size = batch_size,shuffle=False,num_workers=0)

num_inputs ,num_outputs,num_hiddens = 784,10,256
class MLP(nn.module):    def __init__(self,num_inputs,num_outputs,num_hiddens):        super(MLP,self).__init__()        #使用父类的初始化参数        self.mlp = nn.Sequential(        	nn.Linear(num_inputs,num_hiddens)            nn.ReLU()            nn.Linear(num_hiddens,num_outputs)        	)        #定义神经网络里的输入、隐藏和输出层            def forward(self,x):    #定义前向传播    	y = self.mlp(x.view(x.shape[0],-1))        reyurn y        net = MLP(x,num_inputs,num_outputs,num_hiddens)

print(net)

loss = torch.nn.CrossEntropyLoss()#损失函数optimizer = torch.optim.SGD(net.paramters(),lr=0.5)#优化函数

#argmax(f(x))函数，对f(x)求最大值所对应的点x。我们令f(x)= dim=1，即可实现求所有行上的最大值对应的索引。A = y_hat.argmax(dim=1)	#最终输出结果为一个行数与y_hat相同的列向量

B = (y_hat.argmax(dim=1)==y).float()#由于y_hat.argmax(dim=1)==y得到的是ByteTensor型数据，所以我们通过.float()将其转换为浮点型Tensor()

(y_hat.argmax(dim=1)==y).float().mean()

(y_hat.argmax(dim=1)==y).float().mean().item()#pytorch number的获取统一通过.item()实现

def accuracy(y_hat,y):    return (y_hat.argmax(dim=1).float().mean().item())

def net_accurary(data_iter,net):    right_sum,n = 0.0,0    for X,y in data_iter:    #从迭代器data_iter中获取X和y        right_sum += (net(X).argmax(dim=1)==y).float().sum().item()        #计算准确判断的数量        n +=y.shape[0]        #通过shape[0]获取y的零维度（列）的元素数量    return right_sum/n

num_epochs = 5
def train_MLP(net,train_iter,test_iter,loss,num_epochs,batch_size,optimizer,net_accurary):    for epoch in range(num_epochs):        #损失值、正确数量、总数 初始化。        train_l_sum,train_right_sum,n= 0.0,0.0,0                for X,y in train_iter:            y_hat = net(X)            l = loss(y_hat,y).sum()            #数据集损失函数的值=每个样本的损失函数值的和。            optimizer.zero_grad()			#对优化函数梯度清零            #for param in params:            #    param.grad.data.zero_()            l.backward()	#对损失函数求梯度                        optimizer.step()                        train_l_sum += l.item()            train_right_sum += (y_hat.argmax(dim=1) == y).sum().item()            n += y.shape[0]                    test_acc = net_accurary(test_iter, net)	#测试集的准确率        print('epoch %d, loss %.4f, train right %.3f, test right %.3f' % (epoch + 1, train_l_sum / n, train_right_sum / n, test_acc))        start = time()train_MLP(net,train_iter,test_iter,loss,num_epochs,batch_size,optimizer,net_accurary)print('%.3f'% (time()-start),'s')

#将样本的类别数字转换成文本def get_Fashion_MNIST_labels(labels):    text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat',                   'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']    return [text_labels[int(i)] for i in labels]    #labels是一个列表，所以有了for循环获取这个列表对应的文本列表
#显示图像def show_fashion_mnist(images,labels):    display.set_matplotlib_formats('svg')    #绘制矢量图    _,figs = plt.subplots(1,len(images),figsize=(12,12))    #设置添加子图的数量、大小    for f,img,lbl in zip(figs,images,labels):        f.imshow(img.view(28,28).numpy())        f.set_title(lbl)        f.axes.get_xaxis().set_visible(False)        f.axes.get_yaxis().set_visible(False)    plt.show()
#从测试集中获得样本和标签X, y = iter(test_iter).next()
true_labels = get_Fashion_MNIST_labels(y.numpy())pred_labels = get_Fashion_MNIST_labels(net(X).argmax(dim=1).numpy())
#将真实标签和预测得到的标签加入到图像上titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]
show_fashion_mnist(X[0:9], titles[0:9])