import torch
import torch.nn as nn
from torchvision import  datasets,transforms
from visdom import Visdom

viz = Visdom()


batch_size=200
learning_rate=0.01
epochs=10



train_loader = torch.utils.data.DataLoader(
    datasets.MNIST('../data', train=True, download=True,
                   transform=transforms.Compose([
                       transforms.ToTensor(),
                       transforms.Normalize((0.1307,), (0.3081,))
                   ])),
    batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(
    datasets.MNIST('../data', train=False, transform=transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.1307,), (0.3081,))
    ])),
    batch_size=batch_size, shuffle=True)
class MLP(nn.Module):

    def __init__(self):
        super(MLP,self).__init__()

        self.model = nn.Sequential(
            nn.Linear(784,200),
            nn.ReLU(inplace=True),
            nn.Linear(200,200),
            nn.ReLU(inplace=True),
            nn.Linear(200,10),
            nn.ReLU(inplace=True),
        )

    def forward(self,x):
        x = self.model(x)
        return x

device =torch.device('cuda:0')
net = MLP().to(device)
#weight_decay 权重衰减
optimizer = torch.optim.SGD(net.parameters(),lr=learning_rate,weight_decay=0.01)
criteon = torch.nn.CrossEntropyLoss().to(device)


viz = Visdom()
viz.line([0.],[0.],win='train_loss',opts=dict(title='train loss'))
viz.line([[0.0,0.0]],[0.],win='test',opts=dict(title='test loss&acc',
                                               legend=['loss','acc']))
global_step = 0

for epoch in range(epochs):
    for batch_idx,(data,target) in enumerate(train_loader):
        data = data.view(-1,28*28)
        data,target = data.to(device),target.cuda()
        logits = net(data)
        loss = criteon(logits,target)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        global_step +=1
        viz.line([loss.item()],[global_step],win='train_loss',update='append')
        if batch_idx % 100 == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                       100. * batch_idx / len(train_loader), loss.item()))


    test_loss = 0
    correct = 0
    for data, target in test_loader:
        data = data.view(-1, 28 * 28)
        data,target = data.to(device),target.cuda()

        logits = net(data)
        test_loss += criteon(logits, target).item()

        pred = logits.data.max(1)[1]
        correct += pred.eq(target.data).float().sum().item()
    viz.line([[test_loss,correct/len(test_loader.dataset)]],[global_step],win='test',update='append')
    # viz.images(data.view(-1, 1, 28, 28), win='x')
    # viz.text(str(pred.detach().cpu().numpy()), win='pred',
    #          opts=dict(title='pred'))
    test_loss /= len(test_loader.dataset)
    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))