import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms

# 配置GPU或CPU设置
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

# 超参数设置
num_epochs = 5
num_classes = 10
batch_size = 100
learning_rate = 0.001

# 下载 MNIST dataset
train_dataset = torchvision.datasets.MNIST(root='./data/',
                                           train=True,
                                           transform=transforms.ToTensor(),# 将PIL Image或者 ndarray 转换为tensor，并且归一化至[0-1]，归一化至[0-1]是直接除以255
                                           download=True)

test_dataset = torchvision.datasets.MNIST(root='./data/',
                                          train=False,
                                          transform=transforms.ToTensor())# 将PIL Image或者 ndarray 转换为tensor，并且归一化至[0-1]，归一化至[0-1]是直接除以255

# 训练数据加载，按照batch_size大小加载，并随机打乱
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True)
# 测试数据加载，按照batch_size大小加载
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size,
                                          shuffle=False)

# Convolutional neural network (two convolutional layers) 2层卷积
class ConvNet(nn.Module):
    def __init__(self, num_classes=10):
        super(ConvNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.fc = nn.Linear(7 * 7 * 32, num_classes)

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out


model = ConvNet(num_classes).to(device)
print(model)

# ConvNet(
#   (layer1): Sequential(
#     (0): Conv2d(1, 16, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
#     (1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
#     (2): ReLU()
#     (3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False))
#   (layer2): Sequential(
#     (0): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
#     (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
#     (2): ReLU()
#     (3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False))
#   (fc): Linear(in_features=1568, out_features=10, bias=True))

# 损失函数与优化器设置
# 损失函数
criterion = nn.CrossEntropyLoss()
# 优化器设置 ，并传入CNN模型参数和相应的学习率
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# 训练CNN模型
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)

        # 前向传播
        outputs = model(images)
        # 计算损失 loss
        loss = criterion(outputs, labels)

        # 反向传播与优化
        # 清空上一步的残余更新参数值
        optimizer.zero_grad()
        # 反向传播
        loss.backward()
        # 将参数更新值施加到RNN model的parameters上
        optimizer.step()
        # 每迭代一定步骤，打印结果值
        if (i + 1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
                   .format(epoch + 1, num_epochs, i + 1, total_step, loss.item()))

# 测试模型
# model.train model.eval  在测试模型时在前面使用:model.eval() ; 在训练模型时会在前面加上：model.train()
# 让model变成测试模式,是针对model 在训练时和评价时不同的 Batch Normalization  和  Dropout 方法模式
# eval（）时，让model变成测试模式, pytorch会自动把BN和DropOut固定住，不会取平均，而是用训练好的值,
# 不然的话，一旦test的batch_size过小，很容易就会被BN层导致生成图片颜色失真极大。
model.eval()  # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()
    print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))

# 保存已经训练好的模型
# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')