pytorch之简单的卷积神经网络

网络样例

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

#输入图片的格式是32*32
class Net(nn.Module):

    def __init__(self):#只是定义网络中需要用到的方法
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 3x3 square convolution
        # 32*32的输入
        self.conv1 = nn.Conv2d(1, 6, 3)#30*30*6的输出，卷积之后15*15*6
        self.conv2 = nn.Conv2d(6, 16, 3)#13*13*16的输出，卷积之后6*6*16
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 6 * 6, 120)  # 6*6 from image dimension 
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):#这里是真正建立网络
        # Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        # If the size is a square you can only specify a single number
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(-1, self.num_flat_features(x))#特征平展,num_flat_features函数计算出的数据的维度为16*6*6，对接下一层的输入
        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()
print(net)
输出：
Net(
  (conv1): Conv2d(1, 6, kernel_size=(3, 3), stride=(1, 1))
  (conv2): Conv2d(6, 16, kernel_size=(3, 3), stride=(1, 1))
  (fc1): Linear(in_features=576, out_features=120, bias=True)
  (fc2): Linear(in_features=120, out_features=84, bias=True)
  (fc3): Linear(in_features=84, out_features=10, bias=True)
)

• 关于卷积的参数在注释中说明
• 池化过程的参数计算是 取整，如上例：（13/2）=6，所以fc1层的参数 是1666

cifar分类器

import torch
import torchvision
import torchvision.transforms as transforms

准备数据

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')

构建网络

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(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()

定义优化器和loss

import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)#指定net.parameters()

训练网络

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; data is a list of [inputs, labels]
        inputs, labels = data
        # zero the parameter gradients,把梯度置零，也就是把loss关于weight的导数变成0.
        optimizer.zero_grad()
        # forward + backward + optimize
        outputs = net(inputs)#forward前向传播求出预测的值
        loss = criterion(outputs, labels)#求los
        loss.backward()#backward反向传播求梯度
        optimizer.step()#optimize更新所有参数

        # print statistics
        running_loss += loss.item()
        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')

统计正确率

correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)#得到模型输出
        _, predicted = torch.max(outputs.data, 1)#通过模型输出获取识别标签
        total += labels.size(0)#测试集图片总数
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (
    100 * correct / total))
    输出：
    Accuracy of the network on the 10000 test images: 53 %

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
        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]))
输出：
Accuracy of plane : 47 %
Accuracy of   car : 73 %
Accuracy of  bird : 35 %
Accuracy of   cat : 15 %
Accuracy of  deer : 28 %
Accuracy of   dog : 66 %
Accuracy of  frog : 75 %
Accuracy of horse : 67 %
Accuracy of  ship : 80 %
Accuracy of truck : 40 %