import torch
import torchvision
import numpy as np
from torch import nn
from torch.nn import init
from torch.autograd import Variable
from torch.utils import data
 
EPOCH=20
BATCH_SIZE=64
LR=1e-2
 
train_data=torchvision.datasets.MNIST(root='./mnist',train=True,
                   transform=torchvision.transforms.ToTensor(),download=False)
train_loader=data.DataLoader(train_data,batch_size=BATCH_SIZE,shuffle=True)
 
test_data=torchvision.datasets.MNIST(root='./mnist',train=False)
 
test_x=Variable(torch.unsqueeze(test_data.test_data,dim=1).type(torch.FloatTensor)).cuda()/255
test_y=test_data.test_labels.cuda()
 
class CNN(nn.Module):
  def __init__(self):
    super().__init__()
    self.conv1=nn.Sequential(
        nn.Conv2d(in_channels=1,out_channels=16,kernel_size=4,stride=1,padding=2),
        nn.ReLU(),
        nn.MaxPool2d(kernel_size=2,stride=2))
    self.conv2=nn.Sequential(nn.Conv2d(16,32,4,1,2),nn.ReLU(),nn.MaxPool2d(2,2))
    self.out=nn.Linear(32*7*7,10)
     
  def forward(self,x):
    per_out=[] ############修改处##############
    x=self.conv1(x)
    per_out.append(x) # conv1
    x=self.conv2(x)
    per_out.append(x) # conv2
    x=x.view(x.size(0),-1)
    output=self.out(x)
    return output,per_out
   
cnn=CNN().cuda() # or cnn.cuda()
 
optimizer=torch.optim.Adam(cnn.parameters(),lr=LR)
loss_func=nn.CrossEntropyLoss().cuda()############################
 
for epoch in range(EPOCH):
  for step,(x,y) in enumerate(train_loader):
    b_x=Variable(x).cuda()# if channel==1 auto add c=1
    b_y=Variable(y).cuda()
#    print(b_x.data.shape)
    optimizer.zero_grad()
    output=cnn(b_x)[0] ##原先只需要cnn(b_x) 但是现在需要用到第一个返回值##
    loss=loss_func(output,b_y)# Variable need to get .data
    loss.backward()
    optimizer.step()
     
    if step%50==0:
      test_output=cnn(test_x)[0]
      pred_y=torch.max(test_output,1)[1].cuda().data.squeeze()
      '''
      why data ,because Variable .data to Tensor;and cuda() not to numpy() ,must to cpu and to numpy 
      and .float compute decimal
      '''
      accuracy=torch.sum(pred_y==test_y).data.float()/test_y.size(0)
      print('EPOCH: ',epoch,'| train_loss:%.4f'%loss.data[0],'| test accuracy:%.2f'%accuracy)
    #                       loss.data.cpu().numpy().item() get one value
 
  torch.save(cnn.state_dict(),'./model/model.pth')
 
##输出中间层特征，根据索引调用##
 
conv1: conv1=cnn(b_x)[1][0]
 
conv2: conv2=cnn(b_x)[1][1]