【PyTorch】CNN实现CIFAR10的预测

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

#定义一个卷积神经网络
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5) #默认步长1，padding=0
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120) #5*5表示每个通道卷积输出的大小，
                                    # 因为输出为16通道，因此全连接成一个16*5*5大小向量
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x): #输入过来的inputs是[4,3,32,32]
        x = self.pool(F.relu(self.conv1(x))) #[4,6,14,14]
        x = self.pool(F.relu(self.conv2(x))) #[4,16,5,5]
        x = x.view(-1, 16 * 5 * 5) #view成一个向量
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


def imshow(img):
    img = img/2 +0.5
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()

transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])#初始数据归一化防止数据过大

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=False, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
                                          shuffle=True, num_workers=0)

testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=False, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                         shuffle=False, num_workers=0)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
#print(device)
classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

# get some random training images
# dataiter = iter(trainloader)
# images, labels = dataiter.next()
#
# # show images
# imshow(torchvision.utils.make_grid(images))
# # print labels 根据索引输出标签
# print(' '.join('%5s' % classes[labels[j]] for j in range(4)))
#定义网络
net =Net()
net.to(device)
#定义损失函数
criterion = nn.CrossEntropyLoss() #交叉熵损失一般用于分类问题
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
#训练网络
for epoch in range(2): #循环读入数据集2次
    running_loss = 0.
    for i, data in enumerate(trainloader,0): #从第一个数据开始训练
        # get the inputs; data is a list of [inputs, labels]
        inputs, labels = data[0].to(device), data[1].to(device)
        # print('inputs:',inputs) #inputs:[4,3,32,32],batch_size = 4,三通道彩图，大小32*32
        # print('labels:',labels) #labels:[4]
        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs) #[4,10]
        # print(outputs.shape) #[4],每一列在其余位置补0
        # print(labels.shape)
        loss = criterion(outputs,labels) #相当于此时完成了正向传播
        loss.backward()
        optimizer.step() #对训练参数进行更新

        #print statistics
        running_loss += loss.item()
        if i % 2000 == 1999:   #每2000次batch_size的输入，打印一次结果
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000)) #平均loss
            running_loss = 0.
print('training finished!')
#test data
class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
    for data in testloader:
        images, labels = data[0].to(device), data[1].to(device)
        outputs = net(images)
        _, predicted = torch.max(outputs, 1)
        c = (predicted == labels).squeeze()
        for i in range(4):
            label = labels[i]
            class_correct[label] += c[i].item()
            class_total[label] += 1


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

结果

[1,  2000] loss: 2.164
[1,  4000] loss: 1.821
[1,  6000] loss: 1.667
[1,  8000] loss: 1.563
[1, 10000] loss: 1.477
[1, 12000] loss: 1.434
[2,  2000] loss: 1.358
[2,  4000] loss: 1.337
[2,  6000] loss: 1.329
[2,  8000] loss: 1.294
[2, 10000] loss: 1.264
[2, 12000] loss: 1.256
training finished!
Accuracy of plane : 59 %
Accuracy of   car : 77 %
Accuracy of  bird : 39 %
Accuracy of   cat : 33 %
Accuracy of  deer : 45 %
Accuracy of   dog : 44 %
Accuracy of  frog : 54 %
Accuracy of horse : 65 %
Accuracy of  ship : 73 %
Accuracy of truck : 65 %