import torch
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
import torch.nn.functional as F
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 Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        #把线性层全部连接起来的称为全连接网络
        self.l1=torch.nn.Linear(784,512)
        self.l2=torch.nn.Linear(512,256)
        self.l3=torch.nn.Linear(256,128)
        self.l4=torch.nn.Linear(128,64)
        self.l5=torch.nn.Linear(64,10)
    def forward(self,x):
        x=x.view(-1,784)#变成一行有784个数据
        x=F.relu(self.l1(x))
        x=F.relu(self.l2(x))
        x=F.relu(self.l3(x))
        x=F.relu(self.l4(x))
        return self.l5(x)#最后一层不使用relu激活函数,而是接入到softmax中
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()