import torch
from torch.autograd import Variable
import numpy as np
import matplotlib.pyplot as plt
from torch import nn,optim
from torch.utils.data import DataLoader
from torchvision import datasets,transforms
#定义三层全连接神经网络
class simpleNet(nn.Module):
 def __init__(self,in_dim,n_hidden_1,n_hidden_2,out_dim):#输入维度，第一层的神经元个数、第二层的神经元个数，以及第三层的神经元个数
  super(simpleNet,self).__init__()
  self.layer1=nn.Linear(in_dim,n_hidden_1)
  self.layer2=nn.Linear(n_hidden_1,n_hidden_2)
  self.layer3=nn.Linear(n_hidden_2,out_dim)
 def forward(self,x):
  x=self.layer1(x)
  x=self.layer2(x)
  x=self.layer3(x)
  return x
 
 
#添加激活函数
class Activation_Net(nn.Module):
 def __init__(self,in_dim,n_hidden_1,n_hidden_2,out_dim):
  super(NeutalNetwork,self).__init__()
  self.layer1=nn.Sequential(#Sequential组合结构
  nn.Linear(in_dim,n_hidden_1),nn.ReLU(True))
  self.layer2=nn.Sequential(
  nn.Linear(n_hidden_1,n_hidden_2),nn.ReLU(True))
  self.layer3=nn.Sequential(
  nn.Linear(n_hidden_2,out_dim))
 def forward(self,x):
  x=self.layer1(x)
  x=self.layer2(x)
  x=self.layer3(x)
  return x
#添加批标准化处理模块,皮标准化放在全连接的后面，非线性的前面
class Batch_Net(nn.Module):
 def _init__(self,in_dim,n_hidden_1,n_hidden_2,out_dim):
  super(Batch_net,self).__init__()
  self.layer1=nn.Sequential(nn.Linear(in_dim,n_hidden_1),nn.BatchNormld(n_hidden_1),nn.ReLU(True))
  self.layer2=nn.Sequential(nn.Linear(n_hidden_1,n_hidden_2),nn.BatchNormld(n_hidden_2),nn.ReLU(True))
  self.layer3=nn.Sequential(nn.Linear(n_hidden_2,out_dim))
 def forword(self,x):
  x=self.layer1(x)
  x=self.layer2(x)
  x=self.layer3(x)
  return x
  
  

import torch
from torch.autograd import Variable
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
from torch import nn,optim
from torch.utils.data import DataLoader
from torchvision import datasets,transforms
#定义一些超参数
import net
batch_size=64
learning_rate=1e-2
num_epoches=20
#预处理
data_tf=transforms.Compose(
[transforms.ToTensor(),transforms.Normalize([0.5],[0.5])])#将图像转化成tensor，然后继续标准化，就是减均值，除以方差

#读取数据集
train_dataset=datasets.MNIST(root='./data',train=True,transform=data_tf,download=True)
test_dataset=datasets.MNIST(root='./data',train=False,transform=data_tf)
#使用内置的函数导入数据集
train_loader=DataLoader(train_dataset,batch_size=batch_size,shuffle=True)
test_loader=DataLoader(test_dataset,batch_size=batch_size,shuffle=False)

#导入网络，定义损失函数和优化方法
model=net.simpleNet(28*28,300,100,10)
if torch.cuda.is_available():#是否使用cuda加速
 model=model.cuda()
criterion=nn.CrossEntropyLoss()
optimizer=optim.SGD(model.parameters(),lr=learning_rate)
import net
n_epochs=5
for epoch in range(n_epochs):
 running_loss=0.0
 running_correct=0
 print("epoch {}/{}".format(epoch,n_epochs))
 print("-"*10)
 for data in train_loader:
  img,label=data
  img=img.view(img.size(0),-1)
  if torch.cuda.is_available():
   img=img.cuda()
   label=label.cuda()
  else:
   img=Variable(img)
   label=Variable(label)
  out=model(img)#得到前向传播的结果
  loss=criterion(out,label)#得到损失函数
  print_loss=loss.data.item()
  optimizer.zero_grad()#归0梯度
  loss.backward()#反向传播
  optimizer.step()#优化
  running_loss+=loss.item()
  epoch+=1
  if epoch%50==0:
   print('epoch:{},loss:{:.4f}'.format(epoch,loss.data.item()))
 

#测试网络
model.eval()#将模型变成测试模式
eval_loss=0
eval_acc=0
for data in test_loader:
 img,label=data
 img=img.view(img.size(0),-1)#测试集不需要反向传播，所以可以在前项传播的时候释放内存，节约内存空间
 if torch.cuda.is_available():
  img=Variable(img,volatile=True).cuda()
  label=Variable(label,volatile=True).cuda()
 else:
  img=Variable(img,volatile=True)
  label=Variable(label,volatile=True)
 out=model(img)
 loss=criterion(out,label)
 eval_loss+=loss.item()*label.size(0)
 _,pred=torch.max(out,1)
 num_correct=(pred==label).sum()
 eval_acc+=num_correct.item()
print('test loss:{:.6f},ac:{:.6f}'.format(eval_loss/(len(test_dataset)),eval_acc/(len(test_dataset))))