pytorch图像分类器

如何处理数据

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，已经创建了一个叫做torchvision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转换模块torch.utils.data.DataLoader。
接下来将使用CIFAR10数据集，包含十个类别，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3232。

训练一个图像分类器

1.使用torchvision加载并且归一化CIFAR10的训练和测试数据集

import torch
import torchvision
import torchvision.transforms as transforms

# torchvision数据集的输出范围在[0,1]之间的PILImage，将它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))])
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)
# num_workers:使用多进程加载的进程数，0代表不使用多进程
testset = torchvision.datasets.CIFAR10(root='./data', train=Flase, 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')

import matplotlib.pyplot as plt
import numpy as np
# 展示其中的一些训练图片
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()

# 任意获得一些图片
dataiter = iter(trainloader)
images, labels = dataiter.next()

# 展示图片
imshow(torchvision.utils,make_grid(images))
# 打印标签
print(''.join('%5s' % classes[labels[j]] for j in range(4)))

2.定义一个卷积神经网络

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

# 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)
        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()

3.定义一个损失函数

import torch.optim as optim

#定义一个损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

4.在训练样本数据上训练网络

# 训练
for epoch in range(2):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        
        running_loss += loss.item()
        if i % 2000 == 1999:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0
print('Finished Training')

5.在测试样本上测试网络。

# 测试
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))

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.data, 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]))

6.GPU

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)
net.to(device)
inputs, labels = inputs.to(device), labels.to(device)