import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision
train_data = torchvision.datasets.MNIST(
    root='./mnist/',
    train=True,                                     # this is training data
    transform=torchvision.transforms.ToTensor(),    # Converts a PIL.Image or numpy.ndarray to
                                                    # torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
    download=True,
)

train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
for epoch in range(EPOCH):
    for step, (b_x, b_y) in enumerate(train_loader):   # gives batch data, normalize x when iterate train_loader
    	XXXX
    	XXXX

from torchvision.datasets import ImageFolder
data_transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.5,0.5,0.5], std=[0.5, 0.5, 0.5])
])
dataset = ImageFolder("/home/xxx/learn_pytorch/",transform = data_transform)
train_loader = Data.DataLoader(dataset=dataset, batch_size=BATCH_SIZE, shuffle=True)

transforms.RandomSizedCrop
transforms.RandomHorizontalFlip()

class FaceLandmarksDataset(Dataset):
    """Face Landmarks dataset."""
    def __init__(self, csv_file, root_dir, transform=None):
        """
        Args:
            csv_file (string): Path to the csv file with annotations.
            root_dir (string): Directory with all the images.
            transform (callable, optional): Optional transform to be applied
                on a sample.
        """
        self.landmarks_frame = pd.read_csv(csv_file)
        self.root_dir = root_dir
        self.transform = transform
    def __len__(self):
        return len(self.landmarks_frame)
    def __getitem__(self, idx):
        img_name = os.path.join(self.root_dir,
                                self.landmarks_frame.iloc[idx, 0])
        image = io.imread(img_name)
        landmarks = self.landmarks_frame.iloc[idx, 1:].as_matrix()
        landmarks = landmarks.astype('float').reshape(-1, 2)
        sample = {'image': image, 'landmarks': landmarks}
        if self.transform:
            sample = self.transform(sample)
        return sample

face_dataset = FaceLandmarksDataset(csv_file='faces/face_landmarks.csv',
                                    root_dir='faces/')

for i in range(len(face_dataset)):
    sample = face_dataset[i]
    print(sample['image'])
    print(i,sample['image'].shape, sample['landmarks'].shape)

class ToTensor(object):
    """Convert ndarrays in sample to Tensors."""
    def __call__(self, sample):
        image, landmarks = sample['image'], sample['landmarks']
        # swap color axis because
        # numpy image: H x W x C
        # torch image: C X H X W
        image = image.transpose((2, 0, 1))
        return {'image': torch.from_numpy(image),
                'landmarks': torch.from_numpy(landmarks)}

class Rescale(object):
    """Rescale the image in a sample to a given size.
    Args:
        output_size (tuple or int): Desired output size. If tuple, output is
            matched to output_size. If int, smaller of image edges is matched
            to output_size keeping aspect ratio the same.
    """
    def __init__(self, output_size):
        assert isinstance(output_size, (int, tuple))
        self.output_size = output_size
    def __call__(self, sample):
        image, landmarks = sample['image'], sample['landmarks']
        h, w = image.shape[:2]
        if isinstance(self.output_size, int):
            if h > w:
                new_h, new_w = self.output_size * h / w, self.output_size
            else:
                new_h, new_w = self.output_size, self.output_size * w / h
        else:
            new_h, new_w = self.output_size
        new_h, new_w = int(new_h), int(new_w)
        img = transform.resize(image, (new_h, new_w))
        # h and w are swapped for landmarks because for images,
        # x and y axes are axis 1 and 0 respectively
        landmarks = landmarks * [new_w / w, new_h / h]
        return {'image': img, 'landmarks': landmarks}
class RandomCrop(object):
    """Crop randomly the image in a sample.
    Args:
        output_size (tuple or int): Desired output size. If int, square crop
            is made.
    """
    def __init__(self, output_size):
        assert isinstance(output_size, (int, tuple))
        if isinstance(output_size, int):
            self.output_size = (output_size, output_size)
        else:
            assert len(output_size) == 2
            self.output_size = output_size
    def __call__(self, sample):
        image, landmarks = sample['image'], sample['landmarks']
        h, w = image.shape[:2]
        new_h, new_w = self.output_size
        top = np.random.randint(0, h - new_h)
        left = np.random.randint(0, w - new_w)
        image = image[top: top + new_h,
                      left: left + new_w]
        landmarks = landmarks - [left, top]
        return {'image': image, 'landmarks': landmarks}

transformed_dataset = FaceLandmarksDataset(csv_file='faces/face_landmarks.csv',
                                           root_dir='faces/',
                                           transform=transforms.Compose([
                                               Rescale(256),
                                               RandomCrop(224),
                                               ToTensor()
                                           ]))
for i in range(len(transformed_dataset)):
    sample = transformed_dataset[i]
    print(i, sample['image'].size(), sample['landmarks'].size())
    if i == 3:
        break

        self.transform = transform

        if self.transform:
            sample = self.transform(sample)

dataloader = DataLoader(transformed_dataset, batch_size=4, shuffle=True, num_workers=4)

import os
import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt
from torchvision import transforms
from torchvision.datasets import ImageFolder
import matplotlib.pyplot as plt
%matplotlib inline
#定義幾個(gè)參數(shù)
EPOCH = 20
BATCH_SIZE = 4
LR = 0.001
#讀取數(shù)據(jù)
data_transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.5,0.5,0.5], std=[0.5, 0.5, 0.5])
])
dataset = ImageFolder("/home/xxx/learn_pytorch/",transform = data_transform)
print(dataset[0][0].size())
print(dataset.class_to_idx)
#定義
train_loader = Data.DataLoader(dataset=dataset, batch_size=BATCH_SIZE, shuffle=True)
#定義模型類(lèi)，是 nn.Module的繼承類(lèi)，思路是先把每個(gè)層都定義出來(lái)，每個(gè)都是模型類(lèi)的屬性，然后再定義一個(gè)成員函數(shù)forward()作為前向傳播過(guò)程，就可以把每個(gè)層連起來(lái)了，通過(guò)這個(gè)就搭好了整個(gè)模型
class CNN(nn.Module):
    def __init__(self):
        super(CNN,self).__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d(3,16,5,1,2),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2),
        )
        self.conv2 = nn.Sequential(         
            nn.Conv2d(16, 32, 5, 1, 2),     
            nn.ReLU(),                      
            nn.MaxPool2d(2),                
        )
        self.conv3 = nn.Sequential(         
            nn.Conv2d(32, 64, 5, 1, 2),     
            nn.ReLU(),                      
            nn.MaxPool2d(2),                
        )
        self.conv4 = nn.Sequential(         
            nn.Conv2d(64, 128, 5, 1, 2),     
            nn.ReLU(),                      
            nn.MaxPool2d(2),                
        )
        self.out1 = nn.Sequential(
            nn.Linear(128*16*30, 1000),
            nn.ReLU(),
        )
        self.out2 = nn.Sequential(
            nn.Linear(1000, 100),
            nn.ReLU(),
        )
        self.out3 = nn.Sequential(
            nn.Linear(100, 4),
        )
    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = self.conv3(x)
        x = self.conv4(x)
        x = x.view(x.size(0), -1)           # flatten the output of conv2 to (batch_size, 32 * 7 * 7)
        x = self.out1(x)
        x = self.out2(x)
        output = self.out3(x)
        return output, x    # return x for visualization
#如果使用GPU訓(xùn)練要把模型和tensor放到GPU上，通過(guò).cuda來(lái)實(shí)現(xiàn)
cnn = CNN().cuda()
print(cnn)
#定義優(yōu)化器對(duì)象、損失函數(shù)
optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)   # optimize all cnn parameters
loss_func = nn.CrossEntropyLoss()                       # the target label is not one-hotted
#二重循環(huán)開(kāi)始訓(xùn)練，外層循環(huán)是迭代次數(shù)，第二重循環(huán)就是每次對(duì)batch_size的數(shù)據(jù)讀取并訓(xùn)練
for epoch in range(EPOCH):
    accy_count = 0
    for step,(b_x,b_y) in enumerate(train_loader):
        output = cnn(b_x.cuda())[0]
        loss = loss_func(output,b_y.cuda())     #carcute loss
        optimizer.zero_grad()           #clear gradient
        loss.backward()                 #sovel gradient
        optimizer.step()                #gradient sovel
        output_index = torch.max(output,1)[1].cpu().data.numpy()
        accy_count += float((output_index==b_y.data.numpy()).astype(int).sum())
    accuracy = accy_count/(BATCH_SIZE * train_loader.__len__())
    print("Epoch:",epoch," accuracy is: ",accuracy)