1.导入相关包
#【1】导入相关包
import torch
from torch import nn
from torch.nn import init
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import time
import numpy as np
import sys
sys.path.append("..")#导入本地文件。两个点代表上一层目录。
import my_pytorch as mp
2.获取和读取数据
#【2】获取和读取数据
#【2.1】定义获取label对应的值，及可视化数据（图像）的方法
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0-9的数字组成的list
def show_fashion_mnist(images,labels):
#mp.use_svg_display()
_,figs=plt.subplots(1,len(images),figsize=(12,12))
for f,img,lbl in zip(figs,images,labels):
f.imshow(img.view((28,28)).numpy())#img现在是tensor，要转numpy数组
f.set_title(lbl)
f.axes.get_xaxis().set_visible(False)
f.axes.get_yaxis().set_visible(False)
plt.show()
#【2.2】获取、显示、读取数据
batch_size=256
def load_data_fashion_mnist():
#【2.2.1】使用torchvision.datasets模块下载数据集
mnist_train=torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST',train=False,download=True,transform=transforms.ToTensor())
mnist_test=torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST',train=True,download=True,transform=transforms.ToTensor())
#【2.2.2】查看数据集大小
print(len(mnist_train),len(mnist_test))
#【2.2.3】查看数据属性
feature,label=mnist_train[0]
print(feature.shape,label)#ChannelxHeightxWidth
#输出：torch.Size([1, 28, 28]) tensor(9)
#【2.2.4】显示数据：把训练集的10张图像显示在1行
X,y=[],[]
for i in range(10):#显示10张图像
X.append(mnist_train[i][0])
y.append(mnist_train[i][1])
show_fashion_mnist(X,get_fashion_mnist_labels(y))
#【2.2.5】小批量读取数据
if sys.platform.startswith('win'):
num_workers.=0
else:
num_workers=4
train_iter=torcn.utils.data.DataLoader(mnist_train,batch_size=batch_size,num_workers=num_workers)
test_iter=torcn.utils.data.DataLoader(mnist_test,batch_size=batch_size,num_workers=num_workers)
#【2.3】调用读取数据的方法，返回train和test的迭代器
train_iter,test_iter=load_data_fashion_mnist(batch_size)
3.初始化模型参数
#【3】初始化模型参数
num_inputs=784 #28x28
num_outputs=10
W=torch.tensor(np.random.normal(0,0.01,(num_inputs,num_outputs),dtype=torch.float))
b=torch.zeros(num_outputs,dtype=torch.float)
W.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)
4.实现softmax运算
演示tensor的按行、按列求和：
#演示tensor的按行、按列求和
X=torch.tensor([[1,2,3],[4,5,6]])#2x3
print(X.sum(dim=0,keepdim=True))#tensor([[5, 7, 9]])
print(X.sum(dim=1,keepdim=True))
#tensor([[ 6],
# [15]])
softmax函数实现：
#【4】实现softmax函数
def softmax(X):
X_exp=X.exp()
partition=X.exp.sum(dim=1,keepdim=True)
return X_exp/partition
#测试softmax函数：
X=torch.rand(2,5)
X_prob=softmax(X)
print(X_prob,X_prob.sum(dim=1))#得到的每一行值都为1
5.定义模型
#【5】定义模型
def net(X):
return softmax(torch.mm(X.view(-1,num_inputs)),W)+b)#X是（C,H,W）的Tensor。W是784x10的Tensor。b是10x1的Tensor。
6.定义损失函数
gather函数演示：
y_hat=torch.tensor([[0.1,0.3,0.6],[0.3,0.2,0.5]])#2个样本在3个类别的预测概率
y=torch.LongTensor([0,2])#这2个样本的标签类别
y_hat.gather(1,y.view(-1,1))#得到2个样本的标签的预测概率
输出：
tensor([[0.1000],
[0.5000]])
定义交叉熵损失函数：
#交叉熵损失函数
def cross_entropy(y_hat,y):
return -torch.log(y_hat.gather(1,y.view(-1,1)))
7.计算分类准确率
定义准确率accuracy函数：
def accuracy(y_hat,y):
return (y_hat.argmax(dim=1)==y).float().mean().item()
y_hat.argmax(dim=1)返回矩阵y_hat每行中最大元素的索引，且返回结果与变量y形状相同。(y_hat.argmax(dim=1) == y)是一个类型为ByteTensor的Tensor，我们用float()将其转换为值为0（相等为假）或1（相等为真）的浮点型Tensor。
评价模型net在数据集data_iter上的准确率：
def evaluate_accuracy(data_iter,net):
acc_sum,n=0.0,0
for X,y in data_iter:
acc_sum+=(net(X).argmax(dim=1)==y).float().sum().item()
n+=y.shape[0]
return acc_sum/n
8.训练模型
num_epochs,lr=5,0.1
def train(net,train_iter,test_iter,loss,num_epochs,batch_size, params=None,lr=None,optimizer=None):
for epoch in range(num_epochs):
train_l_sum,train_acc_sum,n=0.0,0.0,0#为了计算损失、准确率
for X,y in train_iter:#在每一个batch_size中
y_hat=net(X)
l=loss(y_hat,y).sum()
#梯度清零
if optimizer is not None:
optimizer.zero_grad()
elif params is not None and params[0].grad is not None:
for param in params:
param.grad.data.zero_()
l.backward()#计算梯度
if optimizer is None:
mp.sgd(params,lr,batch_size)
else:
optimizer.step()
train_l_sum+=l.item()#累加loss
train_acc_sum+=(y_hat.argmax(dim=1)==y).sum().item()#累加准确个数
n+=y.shape[0]
test_acc=evaluate_accuracy(test_iter,net)
print('epoch %d,loss %.4f,train acc %.3f,test acc %.3f'
% (epoch+1,train_l_sum/n,train_acc_sum/n,test_acc))
#调用训练函数
train(net,train_iter,test_iter,cross_entropy,num_epochs,batch_size,[W,b],lr)
9.预测
X,y=iter(test_iter).next()
true_labels=mp.get_fashion_mnist_labels(y.numpy())
pred_labels=mp.get_fashion_mnist_labels(net(X).argmax(dim=1).numpy())
titles=[true+'\n'+pred for true,pred in zip(true_labels,pred_labels)
mp.show_fashion_mnist(X[0:9],titles[0:9])
