Pytorch 训练分类器——CIFAR-10分类

数据处理概述

通常来说，当处理图像，文本，语音或者视频数据时，可以使用标准 python 包将数据加载成 numpy 数组格式，然后将这个数组转换成 torch.*Tensor。

• 对于图像，可以用 Pillow，OpenCV
• 对于语音，可以用 scipy，librosa
• 对于文本，可以直接用 Python 或 Cython 基础数据加载模块，或者用 NLTK 和 SpaCy

特别是对于视觉，我们已经创建了一个叫做 totchvision 的包，该包含有支持加载类似Imagenet，CIFAR10，MNIST 等公共数据集的数据加载模块 torchvision.datasets 和支持加载图像数据数据转换模块 torch.utils.data.DataLoader。
下面，我们将使用CIFAR10数据集，它包含十个类别：‘airplane’, ‘automobile’, ‘bird’, ‘cat’, ‘deer’, ‘dog’, ‘frog’, ‘horse’, ‘ship’, ‘truck’。CIFAR-10 中的图像尺寸为33232，也就是RGB的3层颜色通道，每层通道内的尺寸为32*32。

构造图像分类器

我们将按次序的做如下几步：

1. 使用torchvision加载并且归一化CIFAR10的训练和测试数据集
2. 定义一个卷积神经网络
3. 定义一个损失函数
4. 在训练样本数据上训练网络
5. 在测试样本数据上测试网络

加载数据

加载并归一化 CIFAR10,使用 torchvision ,用它来加载 CIFAR10 数据非常简单。

import torch
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np

#torchvision 数据集的输出是范围在[0,1]之间的 PILImage，我们将他们转换成归一化范围为[-1,1]之间的张量 Tensors
transform = transforms.Compose(
    [transforms.ToTensor(),# 转为Tensor
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])#归一化，前面参数是均值，后面是标准差
#获取训练数据
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=0)#num_works 表示线程的个数，如果电脑上带GPU，可设置多个线程
#获取测试数据
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=0)

classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
def imshow(img):
    img = img / 2 + 0.5     # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()

# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()

# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))

输出结果：

 frog  frog   car   cat

定义卷积神经网络

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()

定义损失函数和优化器

import torch.optim as optim

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

训练网络，只需要在数据迭代器上循环传给网络和优化器 输入就可以。

import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
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
        inputs, labels = data

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # 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')

输出结果：

[1,  2000] loss: 2.206
[1,  4000] loss: 1.839
[1,  6000] loss: 1.665
[1,  8000] loss: 1.593
[1, 10000] loss: 1.528
[1, 12000] loss: 1.477
[2,  2000] loss: 1.394
[2,  4000] loss: 1.373
[2,  6000] loss: 1.330
[2,  8000] loss: 1.325
[2, 10000] loss: 1.283
[2, 12000] loss: 1.268
Finished Training

测试

outputs = net(images)
_, predicted = torch.max(outputs, 1)

print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
                              for j in range(4)))
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 

输出结果：

 deer horse   cat plane
[1,  2000] loss: 2.164
[1,  4000] loss: 1.843
[1,  6000] loss: 1.646
[1,  8000] loss: 1.571
[1, 10000] loss: 1.518
[1, 12000] loss: 1.466
[2,  2000] loss: 1.406
[2,  4000] loss: 1.370
[2,  6000] loss: 1.348
[2,  8000] loss: 1.309
[2, 10000] loss: 1.296
[2, 12000] loss: 1.287
Finished Training
Predicted:   deer  bird   dog  ship
Accuracy of the network on the 10000 test images: 54 %

从图中可以看出，精确度有54%，说明网络有学到东西。

全部代码

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

#torchvision 数据集的输出是范围在[0,1]之间的 PILImage，我们将他们转换成归一化范围为[-1,1]之间的张量 Tensors
transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])#前面参数是均值，后面是标准差
#获取训练数据
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=0)#num_works = 0表示没有子进程
#获取测试数据
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=0)

classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
def imshow(img):
    img = img / 2 + 0.5     # 非规范化
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()

# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()

# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))

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()

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
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
        inputs, labels = data

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # 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')
outputs = net(images)
_, predicted = torch.max(outputs, 1)

print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
                              for j in range(4)))
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))