Pytorch训练CNN分类器的Demo

Training an image classifier
1. Load and normalizing the CIFAR10 datasets  # data
2. Define a Convolutional Neural Network      # net
3. Define a loss function                     # loss
4. Train the network on the training data     # train
5. Test the network on the test data          # test

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


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):
        # img------conv-----pool-----conv------pool----view--liner--liner--liner
        # 32*32*3--28*28*6--14*14*6--10*10*16--5*5*16--400---120----84-----10
        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


if __name__ == "__main__":
    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')

    net = Net()                                                       # 网络结构
    criterion = nn.CrossEntropyLoss()                                 # loss
    optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)   # 优化器
    for epoch in range(2):
        running_loss = 0.0
        for i, data in enumerate(trainloader, 0):
            inputs, labels = data              # get the inputs  [4,3,32,32]  [4]
            optimizer.zero_grad()              # zero the parameter gradients
            outputs = net(inputs)              # forward
            loss = criterion(outputs, labels)  # loss --outputs:4*10  --labels:4
            loss.backward()                    # backward
            optimizer.step()                   # optimize
            running_loss += loss.item()        # loss accumulate
            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')

    dataiter = iter(testloader)
    images, labels = dataiter.next()
    print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
    outputs = net(images)
    _, predicted = torch.max(outputs, 1)
    print('Predicted: ', ' '.join('%5s' % classes[predicted[j]] for j in range(4)))

    # 准确率统计
    correct = 0
    total = 0
    with torch.no_grad():
        for data in testloader:
            images, labels = data
            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))