import numpy as np
from torch import nn, optim
from torch.autograd import Variable
from torchvision import datasets, transforms
from torch.utils.data import DataLoader
import torch


# 训练集
train_dataset = datasets.MNIST(root='./',
                               train=True,
                               transform=transforms.ToTensor(),
                               download=True)
# 测试集
test_dataset = datasets.MNIST(root='./',
                              train=False,
                              transform=transforms.ToTensor(),
                              download=True)
# 批次大小
batch_size = 64

# 装载训练集
train_loader = DataLoader(dataset=train_dataset,
                          batch_size=batch_size,
                          shuffle=True)

# 装载训练集
test_loader = DataLoader(dataset=test_dataset,
                         batch_size=batch_size,
                         shuffle=True)

for i, data in enumerate(train_loader):
    inputs, labels = data
    print(inputs.shape)
    print(labels.shape)
    break


# 定义网络结构
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.layer1 = nn.Sequential(nn.Linear(784, 500), nn.Dropout(p=0.5), nn.Tanh())
        self.layer2 = nn.Sequential(nn.Linear(500, 300), nn.Dropout(p=0.5), nn.Tanh())
        self.layer3 = nn.Sequential(nn.Linear(300, 10), nn.Softmax(dim=1))

    def forward(self, x):
        # ([64, 1, 28, 28])->(64,784)
        x = x.view(x.size()[0], -1)
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        return x



LR = 0.5
# 定义模型
model = Net()
# 定义代价函数
mse_loss = nn.CrossEntropyLoss()
# 定义优化器
optimizer = optim.SGD(model.parameters(), LR)


def train():
    # 训练状态
    model.train()
    for i, data in enumerate(train_loader):
        # 获得一个批次的数据和标签
        inputs, labels = data
        # 获得模型预测结果（64,10）
        out = model(inputs)
        # 交叉熵代价函数out(batch,C), labels(batch)
        loss = mse_loss(out, labels)
        # 梯度清0
        optimizer.zero_grad()
        # 计算梯度
        loss.backward()
        # 修改权值
        optimizer.step()


def test():
    # 测试状态
    model.eval()
    correct = 0
    for i, data in enumerate(test_loader):
        # 获得一个批次的数据和标签
        inputs, labels = data
        # 获得模型预测结果（64,10）
        out = model(inputs)
        # 获得最大值，以及最大值所在的位置
        _, predicted = torch.max(out, 1)
        # 预测正确的数量
        correct += (predicted == labels).sum()
    print("Test acc:{0}".format(correct.item() / len(test_dataset)))

    correct = 0
    for i, data in enumerate(train_loader):
        # 获得一个批次的数据和标签
        inputs, labels = data
        # 获得模型预测结果（64,10）
        out = model(inputs)
        # 获得最大值，以及最大值所在的位置
        _, predicted = torch.max(out, 1)
        # 预测正确的数量
        correct += (predicted == labels).sum()
    print("Train acc:{0}".format(correct.item() / len(train_dataset)))

for epoch in range(20):
    print('epoch:', epoch)
    train()
    test()