import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
import torchvision
from torch.autograd import Variable
from torch.utils.data import DataLoader
import cv2

# 下載訓練集
train_dataset = datasets.MNIST(root='./num/',
                train=True,
                transform=transforms.ToTensor(),
                download=True)
# 下載測試集
test_dataset = datasets.MNIST(root='./num/',
               train=False,
               transform=transforms.ToTensor(),
               download=True)

# dataset 參數(shù)用于指定我們載入的數(shù)據(jù)集名稱
# batch_size參數(shù)設(shè)置了每個包中的圖片數(shù)據(jù)個數(shù)
# 在裝載的過程會將數(shù)據(jù)隨機打亂順序并進打包

# 裝載訓練集
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                      batch_size=batch_size,
                      shuffle=True)
# 裝載測試集
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                     batch_size=batch_size,
                     shuffle=True)

images, labels = next(iter(data_loader_train))
img = torchvision.utils.make_grid(images)

img = img.numpy().transpose(1, 2, 0)
std = [0.5, 0.5, 0.5]
mean = [0.5, 0.5, 0.5]
img = img * std + mean
print(labels)
cv2.imshow('win', img)
key_pressed = cv2.waitKey(0)

# 卷積層使用 torch.nn.Conv2d
# 激活層使用 torch.nn.ReLU
# 池化層使用 torch.nn.MaxPool2d
# 全連接層使用 torch.nn.Linear

class LeNet(nn.Module):
  def __init__(self):
    super(LeNet, self).__init__()
    self.conv1 = nn.Sequential(nn.Conv2d(1, 6, 3, 1, 2), nn.ReLU(),
                  nn.MaxPool2d(2, 2))

    self.conv2 = nn.Sequential(nn.Conv2d(6, 16, 5), nn.ReLU(),
                  nn.MaxPool2d(2, 2))

    self.fc1 = nn.Sequential(nn.Linear(16 * 5 * 5, 120),
                 nn.BatchNorm1d(120), nn.ReLU())

    self.fc2 = nn.Sequential(
      nn.Linear(120, 84),
      nn.BatchNorm1d(84),
      nn.ReLU(),
      nn.Linear(84, 10))
    	# 最后的結(jié)果一定要變?yōu)?10，因為數(shù)字的選項是 0 ~ 9

  def forward(self, x):
    x = self.conv1(x)
    x = self.conv2(x)
    x = x.view(x.size()[0], -1)
    x = self.fc1(x)
    x = self.fc2(x)
    x = self.fc3(x)
    return x

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
batch_size = 64
LR = 0.001

net = LeNet().to(device)
# 損失函數(shù)使用交叉熵
criterion = nn.CrossEntropyLoss()
# 優(yōu)化函數(shù)使用 Adam 自適應(yīng)優(yōu)化算法
optimizer = optim.Adam(
  net.parameters(),
  lr=LR,
)

epoch = 1
if __name__ == '__main__':
  for epoch in range(epoch):
    sum_loss = 0.0
    for i, data in enumerate(train_loader):
      inputs, labels = data
      inputs, labels = Variable(inputs).cuda(), Variable(labels).cuda()
      optimizer.zero_grad() #將梯度歸零
      outputs = net(inputs) #將數(shù)據(jù)傳入網(wǎng)絡(luò)進行前向運算
      loss = criterion(outputs, labels) #得到損失函數(shù)
      loss.backward() #反向傳播
      optimizer.step() #通過梯度做一步參數(shù)更新

      # print(loss)
      sum_loss += loss.item()
      if i % 100 == 99:
        print('[%d,%d] loss:%.03f' %
           (epoch + 1, i + 1, sum_loss / 100))
        sum_loss = 0.0

net.eval() #將模型變換為測試模式
  correct = 0
  total = 0
  for data_test in test_loader:
    images, labels = data_test
    images, labels = Variable(images).cuda(), Variable(labels).cuda()
    output_test = net(images)
    _, predicted = torch.max(output_test, 1)
    total += labels.size(0)
    correct += (predicted == labels).sum()
  print("correct1: ", correct)
  print("Test acc: {0}".format(correct.item() /
                 len(test_dataset)))