import  torch
import  torch.nn as nn
import  torch.nn.functional as F
import  torch.optim as optim
from    torchvision import datasets, transforms
#超參數(shù)
batch_size=200
learning_rate=0.01
epochs=10
#獲取訓(xùn)練數(shù)據(jù)
train_db = datasets.MNIST('../data', train=True, download=True,   #train=True則得到的是訓(xùn)練集
                   transform=transforms.Compose([                 #transform進(jìn)行數(shù)據(jù)預(yù)處理
                       transforms.ToTensor(),                     #轉(zhuǎn)成Tensor類型的數(shù)據(jù)
                       transforms.Normalize((0.1307,), (0.3081,)) #進(jìn)行數(shù)據(jù)標(biāo)準(zhǔn)化(減去均值除以方差)
                   ]))
#DataLoader把訓(xùn)練數(shù)據(jù)分成多個(gè)小組，此函數(shù)每次拋出一組數(shù)據(jù)。直至把所有的數(shù)據(jù)都拋出。就是做一個(gè)數(shù)據(jù)的初始化
train_loader = torch.utils.data.DataLoader(train_db, batch_size=batch_size, shuffle=True)
#獲取測(cè)試數(shù)據(jù)
test_db = datasets.MNIST('../data', train=False,
                   transform=transforms.Compose([
                        transforms.ToTensor(),
                        transforms.Normalize((0.1307,), (0.3081,))
                   ]))
test_loader = torch.utils.data.DataLoader(test_db, batch_size=batch_size, shuffle=True)
#將訓(xùn)練集拆分成訓(xùn)練集和驗(yàn)證集
print('train:', len(train_db), 'test:', len(test_db))                              #train: 60000 test: 10000
train_db, val_db = torch.utils.data.random_split(train_db, [50000, 10000])
print('db1:', len(train_db), 'db2:', len(val_db))                                  #db1: 50000 db2: 10000
train_loader = torch.utils.data.DataLoader(train_db, batch_size=batch_size, shuffle=True)
val_loader = torch.utils.data.DataLoader(val_db, batch_size=batch_size, shuffle=True)
class MLP(nn.Module):
    def __init__(self):
        super(MLP, self).__init__()
        self.model = nn.Sequential(         #定義網(wǎng)絡(luò)的每一層,
            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
net = MLP()
#定義sgd優(yōu)化器,指明優(yōu)化參數(shù)、學(xué)習(xí)率，net.parameters()得到這個(gè)類所定義的網(wǎng)絡(luò)的參數(shù)[[w1,b1,w2,b2,...]
optimizer = optim.SGD(net.parameters(), lr=learning_rate)
criteon = nn.CrossEntropyLoss()
for epoch in range(epochs):
    for batch_idx, (data, target) in enumerate(train_loader):
        data = data.view(-1, 28*28)          #將二維的圖片數(shù)據(jù)攤平[樣本數(shù),784]
        logits = net(data)                   #前向傳播
        loss = criteon(logits, target)       #nn.CrossEntropyLoss()自帶Softmax
        optimizer.zero_grad()                #梯度信息清空
        loss.backward()                      #反向傳播獲取梯度
        optimizer.step()                     #優(yōu)化器更新
        if batch_idx % 100 == 0:             #每100個(gè)batch輸出一次信息
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                       100. * batch_idx / len(train_loader), loss.item()))
    #驗(yàn)證集用來檢測(cè)訓(xùn)練是否過擬合
    val_loss = 0
    correct = 0
    for data, target in val_loader:
        data = data.view(-1, 28 * 28)
        logits = net(data)
        val_loss += criteon(logits, target).item()
        pred = logits.data.max(dim=1)[1]
        correct += pred.eq(target.data).sum()
    val_loss /= len(val_loader.dataset)
    print('\nVAL set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        val_loss, correct, len(val_loader.dataset),
        100. * correct / len(val_loader.dataset)))
#測(cè)試集用來評(píng)估
test_loss = 0
correct = 0                                         #correct記錄正確分類的樣本數(shù)
for data, target in test_loader:
    data = data.view(-1, 28 * 28)
    logits = net(data)
    test_loss += criteon(logits, target).item()     #其實(shí)就是criteon(logits, target)的值，標(biāo)量
    pred = logits.data.max(dim=1)[1]                #也可以寫成pred=logits.argmax(dim=1)
    correct += pred.eq(target.data).sum()
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)))

optimizer = torch.optim.SGD(net.parameters(), lr=learning_rate, weight_decay=0.01)

optimizer = torch.optim.SGD(model.parameters(), args=lr, momentum=args.momentum, weight_decay=args.weight_decay)

torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='min', factor=0.1, patience=10, verbose=False, threshold=0.0001, threshold_mode='rel', cooldown=0, min_lr=0, eps=1e-08)

torch.optim.lr_scheduler.StepLR(optimizer, step_size, gamma=0.1, last_epoch=-1)

torch.nn.Dropout(p=dropout_prob)