pytorch实现cifar10的分类

本文针对本人学习pytorch的过程进行记录，并非总结型笔记，只是针对使用过程中常用且重要的操作予以记录，以便日后进行查看。

code

import torch
import torchvision
import torchvision.transforms as transforms

transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])#class torchvision.transforms.Normalize(mean, std)
                                                             #此转换类作用于torch.*Tensor。给定均值(R, G, B)和标准差(R, G, B)，用公式channel = (channel - mean) / std进行规范化


trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=50,
                                          shuffle=True, num_workers=1)

testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=50,
                                         shuffle=False, num_workers=1)

classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

# 3*32*32
from torch.autograd import  Variable
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.Sequential(         # input shape (3, 32, 32)
            nn.Conv2d(
                in_channels=3,              # input height
                out_channels=16,            # n_filters
                kernel_size=5,              # filter size
                stride=1,                   # filter movement/step
                padding=2,                  # if want same width and length of this image after Conv2d, padding=(kernel_size-1)/2 if stride=1
            ),                              # output shape (16, 32, 32)
            nn.ReLU(),                      # activation
            nn.MaxPool2d(kernel_size=2),    # choose max value in 2x2 area, output shape (16, 16, 16)
        )
        self.conv2 = nn.Sequential(         # input shape (16, 16, 16)
            nn.Conv2d(16, 32, 5, 1, 2),     # output shape (32, 16, 16)
            nn.ReLU(),                      # activation
            nn.MaxPool2d(2),                # output shape (32, 8, 8)
        )
        self.out = nn.Linear(32 * 8 * 8, 10)   # fully connected layer, output 10 classes
    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(-1, 32 * 8 * 8,)           # flatten the output of conv2 to (batch_size, 32 * 8 * 8)
        output = self.out(x)
        return output   # return x for visualization

# our model
net = Net()

import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)

if __name__ ==  '__main__':
    # Train the network
    for epoch in range(1):
        for i, data in enumerate(trainloader):
            inputs, labels = data
            inputs, labels = Variable(inputs), Variable(labels)
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()


    print("Finished Training")

    print("Beginning Testing")
    correct = 0
    total = 0
    for data in testloader:
        images, labels = data
        outputs = net(Variable(images))
        predicted = torch.max(outputs, 1)[1].data.numpy()
        total += labels.size(0)
        correct += (predicted == labels.data.numpy()).sum()


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