# 数据处理
import os
import torch
from torch.utils import data
from PIL import Image
import numpy as np
from torchvision import transforms

transform = transforms.Compose([
 transforms.ToTensor(), # 将图片转换为Tensor,归一化至[0,1]
 # transforms.Normalize(mean=[.5, .5, .5], std=[.5, .5, .5]) # 标准化至[-1,1]
])

#定义自己的数据集合
class FlameSet(data.Dataset):
 def __init__(self,root):
  # 所有图片的绝对路径
  imgs=os.listdir(root)
  self.imgs=[os.path.join(root,k) for k in imgs]
  self.transforms=transform

 def __getitem__(self, index):
  img_path = self.imgs[index]
  pil_img = Image.open(img_path)
  if self.transforms:
   data = self.transforms(pil_img)
  else:
   pil_img = np.asarray(pil_img)
   data = torch.from_numpy(pil_img)
  return data

 def __len__(self):
  return len(self.imgs)

if __name__ == '__main__':
 dataSet=FlameSet('./test')
 print(dataSet[0])

# # 训练数据和测试数据的下载
# 训练数据和测试数据的下载
trainDataset = torchvision.datasets.MNIST( # torchvision可以实现数据集的训练集和测试集的下载
  root="./data", # 下载数据，并且存放在data文件夹中
  train=True, # train用于指定在数据集下载完成后需要载入哪部分数据，如果设置为True，则说明载入的是该数据集的训练集部分；如果设置为False，则说明载入的是该数据集的测试集部分。
  transform=transforms.ToTensor(), # 数据的标准化等操作都在transforms中，此处是转换
  download=True # 瞎子啊过程中如果中断，或者下载完成之后再次运行，则会出现报错
)

testDataset = torchvision.datasets.MNIST(
  root="./data",
  train=False,
  transform=transforms.ToTensor(),
  download=True
)

class DealDataset(Dataset):
  """
    读取数据、初始化数据
  """
  def __init__(self, folder, data_name, label_name,transform=None):
    (train_set, train_labels) = load_minist_data.load_data(folder, data_name, label_name) # 其实也可以直接使用torch.load(),读取之后的结果为torch.Tensor形式
    self.train_set = train_set
    self.train_labels = train_labels
    self.transform = transform

  def __getitem__(self, index):

    img, target = self.train_set[index], int(self.train_labels[index])
    if self.transform is not None:
      img = self.transform(img)
    return img, target

  def __len__(self):
    return len(self.train_set)

def load_data(data_folder, data_name, label_name):
 """
    data_folder: 文件目录
    data_name： 数据文件名
    label_name：标签数据文件名
  """
 with gzip.open(os.path.join(data_folder,label_name), 'rb') as lbpath: # rb表示的是读取二进制数据
  y_train = np.frombuffer(lbpath.read(), np.uint8, offset=8)

 with gzip.open(os.path.join(data_folder,data_name), 'rb') as imgpath:
  x_train = np.frombuffer(
    imgpath.read(), np.uint8, offset=16).reshape(len(y_train), 28, 28)
 return (x_train, y_train)

# 实例化这个类，然后我们就得到了Dataset类型的数据，记下来就将这个类传给DataLoader，就可以了。
trainDataset = DealDataset('MNIST_data/', "train-images-idx3-ubyte.gz","train-labels-idx1-ubyte.gz",transform=transforms.ToTensor())
testDataset = DealDataset('MNIST_data/', "t10k-images-idx3-ubyte.gz","t10k-labels-idx1-ubyte.gz",transform=transforms.ToTensor())

# 训练数据和测试数据的装载
train_loader = dataloader.DataLoader(
  dataset=trainDataset,
  batch_size=100, # 一个批次可以认为是一个包，每个包中含有100张图片
  shuffle=False,
)

test_loader = dataloader.DataLoader(
  dataset=testDataset,
  batch_size=100,
  shuffle=False,
)

class NeuralNet(nn.Module):

  def __init__(self, input_num, hidden_num, output_num):
    super(NeuralNet, self).__init__()
    self.fc1 = nn.Linear(input_num, hidden_num)
    self.fc2 = nn.Linear(hidden_num, output_num)
    self.relu = nn.ReLU()

  def forward(self,x):
    x = self.fc1(x)
    x = self.relu(x)
    y = self.fc2(x)
    return y

# 参数初始化
epoches = 5
lr = 0.001
input_num = 784
hidden_num = 500
output_num = 10
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# 产生训练模型对象以及定义损失函数和优化函数
model = NeuralNet(input_num, hidden_num, output_num)
model.to(device)
criterion = nn.CrossEntropyLoss() # 使用交叉熵作为损失函数
optimizer = optim.Adam(model.parameters(), lr=lr)

# 开始循环训练
for epoch in range(epoches): # 一个epoch可以认为是一次训练循环
  for i, data in enumerate(train_loader):
    (images, labels) = data
    images = images.reshape(-1, 28*28).to(device)
    labels = labels.to(device)
    output = model(images) # 经过模型对象就产生了输出
    loss = criterion(output, labels.long()) # 传入的参数: 输出值(预测值), 实际值(标签)
    optimizer.zero_grad() # 梯度清零
    loss.backward()
    optimizer.step()

    if (i+1) % 100 == 0: # i表示样本的编号
      print('Epoch [{}/{}], Loss: {:.4f}'
         .format(epoch + 1, epoches, loss.item())) # {}里面是后面需要传入的变量
                              # loss.item
# 开始测试
with torch.no_grad():
  correct = 0
  total = 0
  for images, labels in test_loader:
    images = images.reshape(-1, 28*28).to(device) # 此处的-1一般是指自动匹配的意思, 即不知道有多少行，但是确定了列数为28 * 28
                           # 其实由于此处28 * 28本身就已经等于了原tensor的大小，所以，行数也就确定了，为1
    labels = labels.to(device)
    output = model(images)
    _, predicted = torch.max(output, 1)
    total += labels.size(0) # 此处的size()类似numpy的shape: np.shape(train_images)[0]
    correct += (predicted == labels).sum().item()
  print("The accuracy of total {} images: {}%".format(total, 100 * correct/total))