from __future__ import print_function
import torch
x = torch.Tensor(5, 3)  # 构造一个未初始化的5*3的矩阵
x = torch.rand(5, 3)  # 构造一个随机初始化的矩阵
x # 此处在notebook中输出x的值来查看具体的x内容
x.size()

#NOTE: torch.Size 事实上是一个tuple, 所以其支持相关的操作*
y = torch.rand(5, 3)

#此处 将两个同形矩阵相加有两种语法结构
x + y # 语法一
torch.add(x, y) # 语法二

# 另外输出tensor也有两种写法
result = torch.Tensor(5, 3) # 语法一
torch.add(x, y, out=result) # 语法二
y.add_(x) # 将y与x相加

# 特别注明：任何可以改变tensor内容的操作都会在方法名后加一个下划线\'_\'
# 例如：x.copy_(y), x.t_(), 这俩都会改变x的值。

#另外python中的切片操作也是资次的。
x[:,1] #这一操作会输出x矩阵的第二列的所有值

# 此处演示tensor和numpy数据结构的相互转换
a = torch.ones(5)
b = a.numpy()

# 此处演示当修改numpy数组之后,与之相关联的tensor也会相应的被修改
a.add_(1)
print(a)
print(b)

# 将numpy的Array转换为torch的Tensor
import numpy as np
a = np.ones(5)
b = torch.from_numpy(a)
np.add(a, 1, out=a)
print(a)
print(b)

# 另外除了CharTensor之外，所有的tensor都可以在CPU运算和GPU预算之间相互转换
# 使用CUDA函数来将Tensor移动到GPU上
# 当CUDA可用时会进行GPU的运算
if torch.cuda.is_available():
    x = x.cuda()
    y = y.cuda()
    x + y

from torch.autograd import Variable
x = Variable(torch.ones(2, 2), requires_grad = True)
y = x + 2
y.creator

# y 是作为一个操作的结果创建的因此y有一个creator 
z = y * y * 3
out = z.mean()

# 现在我们来使用反向传播
out.backward()

# out.backward()和操作out.backward(torch.Tensor([1.0]))是等价的
# 在此处输出 d(out)/dx
x.grad

x = torch.randn(3)
x = Variable(x, requires_grad = True)
y = x * 2
while y.data.norm() < 1000:
    y = y * 2
gradients = torch.FloatTensor([0.1, 1.0, 0.0001])
y.backward(gradients)
x.grad

import torch.nn as nn
import torch.nn.functional as F

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 6, 5) # 1 input image channel, 6 output channels, 5x5 square convolution kernel
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1   = nn.Linear(16*5*5, 120) # an affine operation: y = Wx + b
        self.fc2   = nn.Linear(120, 84)
        self.fc3   = nn.Linear(84, 10)

    def forward(self, x):
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2)) # Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv2(x)), 2) # If the size is a square you can only specify a single number
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x
    
    def num_flat_features(self, x):
        size = x.size()[1:] # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features

net = Net()
net

\'\'\'神经网络的输出结果是这样的
Net (
  (conv1): Conv2d(1, 6, kernel_size=(5, 5), stride=(1, 1))
  (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
  (fc1): Linear (400 -> 120)
  (fc2): Linear (120 -> 84)
  (fc3): Linear (84 -> 10)
)
\'\'\'

params = list(net.parameters())
print(len(params))
print(params[0].size()) # conv1\'s .weight

input = Variable(torch.randn(1, 1, 32, 32))
out = net(input)
\'\'\'out 的输出结果如下
Variable containing:
-0.0158 -0.0682 -0.1239 -0.0136 -0.0645  0.0107 -0.0230 -0.0085  0.1172 -0.0393
[torch.FloatTensor of size 1x10]
\'\'\'

net.zero_grad() # 对所有的参数的梯度缓冲区进行归零
out.backward(torch.randn(1, 10)) # 使用随机的梯度进行反向传播

output = net(input)
target = Variable(torch.range(1, 10))  # a dummy target, for example
criterion = nn.MSELoss()
loss = criterion(output, target)
\'\'\'loss的值如下
Variable containing:
 38.5849
[torch.FloatTensor of size 1]
\'\'\'

input -> conv2d -> relu -> maxpool2d -> conv2d -> relu -> maxpool2d  
      -> view -> linear -> relu -> linear -> relu -> linear 
      -> MSELoss
      -> loss

# For illustration, let us follow a few steps backward
print(loss.creator) # MSELoss
print(loss.creator.previous_functions[0][0]) # Linear
print(loss.creator.previous_functions[0][0].previous_functions[0][0]) # ReLU

\'\'\'



\'\'\'

# 现在我们应当调用loss.backward(), 之后来看看 conv1\'s在进行反馈之后的偏置梯度如何
net.zero_grad() # 归零操作
print(\'conv1.bias.grad before backward\')
print(net.conv1.bias.grad)
loss.backward()
print(\'conv1.bias.grad after backward\')
print(net.conv1.bias.grad)

\'\'\' 这些步骤的输出结果如下
conv1.bias.grad before backward
Variable containing:
 0
 0
 0
 0
 0
 0
[torch.FloatTensor of size 6]

conv1.bias.grad after backward
Variable containing:
 0.0346
-0.0141
 0.0544
-0.1224
-0.1677
 0.0908
[torch.FloatTensor of size 6]
\'\'\'

learning_rate = 0.01
for f in net.parameters():
    f.data.sub_(f.grad.data * learning_rate)

import torch.optim as optim
# create your optimizer
optimizer = optim.SGD(net.parameters(), lr = 0.01)

# in your training loop:
optimizer.zero_grad() # zero the gradient buffers
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step() # Does the update

import torchvision
import torchvision.transforms as transforms


# torchvision数据集的输出是在[0, 1]范围内的PILImage图片。
# 我们此处使用归一化的方法将其转化为Tensor，数据范围为[-1, 1]

transform=transforms.Compose([transforms.ToTensor(),
                              transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
                             ])
trainset = torchvision.datasets.CIFAR10(root=\'./data\', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, 
                                          shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root=\'./data\', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4, 
                                          shuffle=False, num_workers=2)
classes = (\'plane\', \'car\', \'bird\', \'cat\',
           \'deer\', \'dog\', \'frog\', \'horse\', \'ship\', \'truck\')
\'\'\'注：这一部分需要下载部分数据集 因此速度可能会有一些慢 同时你会看到这样的输出

Downloading http://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to ./data/cifar-10-python.tar.gz
Extracting tar file
Done!
Files already downloaded and verified
\'\'\'

# functions to show an image
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline
def imshow(img):
    img = img / 2 + 0.5 # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1,2,0)))

# show some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()

# print images
imshow(torchvision.utils.make_grid(images))
# print labels
print(\' \'.join(\'%5s\'%classes[labels[j]] for j in range(4)))

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool  = nn.MaxPool2d(2,2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1   = nn.Linear(16*5*5, 120)
        self.fc2   = nn.Linear(120, 84)
        self.fc3   = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16*5*5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

net = Net()

criterion = nn.CrossEntropyLoss() # use a Classification Cross-Entropy loss
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

for epoch in range(2): # loop over the dataset multiple times
    
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs
        inputs, labels = data
        
        # wrap them in Variable
        inputs, labels = Variable(inputs), Variable(labels)
        
        # zero the parameter gradients
        optimizer.zero_grad()
        
        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()        
        optimizer.step()
        
        # print statistics
        running_loss += loss.data[0]
        if i % 2000 == 1999: # print every 2000 mini-batches
            print(\'[%d, %5d] loss: %.3f\' % (epoch+1, i+1, running_loss / 2000))
            running_loss = 0.0
print(\'Finished Training\')
\'\'\'这部分的输出结果为
[1,  2000] loss: 2.212
[1,  4000] loss: 1.892
[1,  6000] loss: 1.681
[1,  8000] loss: 1.590
[1, 10000] loss: 1.515
[1, 12000] loss: 1.475
[2,  2000] loss: 1.409
[2,  4000] loss: 1.394
[2,  6000] loss: 1.376
[2,  8000] loss: 1.334
[2, 10000] loss: 1.313
[2, 12000] loss: 1.264
Finished Training
\'\'\'

dataiter = iter(testloader)
images, labels = dataiter.next()

# print images
imshow(torchvision.utils.make_grid(images))
print(\'GroundTruth: \', \' \'.join(\'%5s\'%classes[labels[j]] for j in range(4)))

outputs = net(Variable(images))

# the outputs are energies for the 10 classes. 
# Higher the energy for a class, the more the network 
# thinks that the image is of the particular class

# So, let\'s get the index of the highest energy
_, predicted = torch.max(outputs.data, 1)

print(\'Predicted: \', \' \'.join(\'%5s\'% classes[predicted[j][0]] for j in range(4)))

\'\'\'输出结果为
Predicted:    cat plane   car plane
\'\'\'

correct = 0
total = 0
for data in testloader:
    images, labels = data
    outputs = net(Variable(images))
    _, predicted = torch.max(outputs.data, 1)
    total += labels.size(0)
    correct += (predicted == labels).sum()

print(\'Accuracy of the network on the 10000 test images: %d %%\' % (100 * correct / total))

\'\'\'输出结果为
Accuracy of the network on the 10000 test images: 54 %
\'\'\'

class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
for data in testloader:
    images, labels = data
    outputs = net(Variable(images))
    _, predicted = torch.max(outputs.data, 1)
    c = (predicted == labels).squeeze()
    for i in range(4):
        label = labels[i]
        class_correct[label] += c[i]
        class_total[label] += 1

for i in range(10):
    print(\'Accuracy of %5s : %2d %%\' % (classes[i], 100 * class_correct[i] / class_total[i]))

\'\'\'输出结果为
Accuracy of plane : 73 %
Accuracy of   car : 70 %
Accuracy of  bird : 52 %
Accuracy of   cat : 27 %
Accuracy of  deer : 34 %
Accuracy of   dog : 37 %
Accuracy of  frog : 62 %
Accuracy of horse : 72 %
Accuracy of  ship : 64 %
Accuracy of truck : 53 %
\'\'\'

net.cuda()

\'\'\'输出结果为
Net (
  (conv1): Conv2d(3, 6, kernel_size=(5, 5), stride=(1, 1))
  (pool): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
  (fc1): Linear (400 -> 120)
  (fc2): Linear (120 -> 84)
  (fc3): Linear (84 -> 10)
)
\'\'\'

    inputs, labels = Variable(inputs.cuda()), Variable(labels.cuda())