import torch
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

# 使用GPU訓練，可以在選單 "程式碼執行工具" -> "更改執行時型別" 裡進行設定
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

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=64,
                                          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=8,
                                         shuffle=False, num_workers=2)

classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
           
#下面展示 CIFAR10 裡面的一些圖片：
def imshow(img):
    plt.figure(figsize=(8,8))
    img = img / 2 + 0.5     # 轉換到 [0,1] 之間
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()
# 得到一組影象
images, labels = iter(trainloader).next()
# 展示影象
imshow(torchvision.utils.make_grid(images))
# 展示第一行影象的標籤
for j in range(8):
    print(classes[labels[j]])
 
#接下來定義網路，損失函式和優化器
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

# 網路放到GPU上
net = Net().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)

#訓練網路：
for epoch in range(10):  # 重複多輪訓練
    for i, (inputs, labels) in enumerate(trainloader):
        inputs = inputs.to(device)
        labels = labels.to(device)
        # 優化器梯度歸零
        optimizer.zero_grad()
        # 正向傳播 +　反向傳播 + 優化 
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        # 輸出統計資訊
        if i % 100 == 0:   
            print('Epoch: %d Minibatch: %5d loss: %.3f' %(epoch + 1, i + 1, loss.item()))

print('Finished Training')

#現在我們從測試集中取出8張圖片：
# 得到一組影象
images, labels = iter(testloader).next()
# 展示影象
imshow(torchvision.utils.make_grid(images))
# 展示影象的標籤
for j in range(8):
    print(classes[labels[j]])
我們把圖片輸入模型，看看CNN把這些圖片識別成什麼：
outputs = net(images.to(device))
_, predicted = torch.max(outputs, 1)

# 展示預測的結果
for j in range(8):
    print(classes[predicted[j]])
    
#網路在整個資料集上的表現：
correct = 0
total = 0

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

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