import torch
import torch.nn.functional as F
from torchvision import transforms#是一个常用的图片变换类
from torchvision import datasets
from torch.utils.data import DataLoader
batch_size=64
transform=transforms.Compose(
    [
        transforms.ToTensor(),#把数据转换成张量
        transforms.Normalize((0.1307,),(0.3081,))#0.1307是均值，0.3081是标准差
    ]
)
train_dataset=datasets.MNIST(root='../dataset/mnist',
                             train=True,
                             download=True,
                             transform=transform)
train_loader=DataLoader(train_dataset,
                        shuffle=True,
                        batch_size=batch_size)
test_dataset=datasets.MNIST(root='../dataset/mnist',
                            train=False,
                            download=True,
                            transform=transform)
test_loader=DataLoader(test_dataset,
                       shuffle=True,
                       batch_size=batch_size)
class InceptionA(torch.nn.Module):
    def __init__(self,in_channels):
        super(InceptionA, self).__init__()
        self.branch1x1=torch.nn.Conv2d(in_channels,16,kernel_size=1)

        self.branch5x5_1=torch.nn.Conv2d(in_channels,16,kernel_size=1)
        self.branch5x5_2=torch.nn.Conv2d(16,24,kernel_size=5,padding=2)

        self.branch3x3_1=torch.nn.Conv2d(in_channels,16,kernel_size=1)
        self.branch3x3_2=torch.nn.Conv2d(16,24,kernel_size=3,padding=1)
        self.branch3x3_3=torch.nn.Conv2d(24,24,kernel_size=3,padding=1)

        self.branch_pool=torch.nn.Conv2d(in_channels,24,kernel_size=1)

    def forward(self,x):
        branch1x1=self.branch1x1(x)

        branch5x5=self.branch5x5_1(x)
        branch5x5=self.branch5x5_2(branch5x5)

        branch3x3=self.branch3x3_1(x)
        branch3x3=self.branch3x3_2(branch3x3)
        branch3x3=self.branch3x3_3(branch3x3)

        branch_pool=F.avg_pool2d(x,kernel_size=3,stride=1,padding=1)
        branch_pool=self.branch_pool(branch_pool)

        outputs=[branch1x1,branch5x5,branch3x3,branch_pool]
        return torch.cat(outputs,dim=1)

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1=torch.nn.Conv2d(1,10,kernel_size=5)
        self.conv2=torch.nn.Conv2d(88,20,kernel_size=5)

        self.incep1=InceptionA(in_channels=10)
        self.incep2=InceptionA(in_channels=20)

        self.mp=torch.nn.MaxPool2d(2)
        self.fc=torch.nn.Linear(1408,10)
    def forward(self,x):
        in_size=x.size(0)
        x=F.relu(self.mp(self.conv1(x)))
        x=self.incep1(x)
        x=F.relu(self.mp(self.conv2(x)))
        x=self.incep2(x)
        x=x.view(in_size,-1)
        x=self.fc(x)
        return x
model=Net()
criterion=torch.nn.CrossEntropyLoss() #使用交叉熵损失
optimizer=torch.optim.SGD(model.parameters(),lr=0.1,momentum=0.5)#momentum表示冲量，冲出局部最小
def train(epochs):
    running_loss=0.0
    for batch_idx,data in enumerate(train_loader,0):
        inputs,target=data
        optimizer.zero_grad()
        #前馈+反馈+更新
        outputs=model(inputs)
        loss=criterion(outputs,target)
        loss.backward()
        optimizer.step()

        running_loss+=loss.item()
        if batch_idx%300==299:#不让他每一次小的迭代就输出，而是300次小迭代再输出一次
            print('[%d,%5d] loss:%.3f'%(epoch+1,batch_idx+1,running_loss/300))
            running_loss=0.0

def test():
    correct=0
    total=0
    with torch.no_grad():#下面的代码就不会再计算梯度
        for data in test_loader:
            images,labels=data
            outputs=model(images)
            _,predicted=torch.max(outputs.data,dim=1)#_为每一行的最大值，predicted表示每一行最大值的下标
            total+=labels.size(0)
            correct+=(predicted==labels).sum().item()
    print('Accuracy on test set:%d %%'%(100*correct/total))
if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()