用pytorch進行CIFAR-10數據集分類

CIFAR-10.（Canadian Institute for Advanced Research）是由 Alex Krizhevsky、Vinod Nair 與 Geoffrey Hinton 收集的一個用於圖像識別的數據集，60000個32*32的彩色圖像，50000個training data，10000個 test data 有10類，飛機、汽車、鳥、貓、鹿、狗、青蛙、馬、船、卡車，每類6000張圖。與MNIST相比，色彩、顏色噪點較多，同一類物體大小不一、角度不同、顏色不同。

 

 先要對該數據集進行分類

步驟如下：
1.使用torchvision加載並預處理CIFAR-10數據集、
2.定義網絡
3.定義損失函數和優化器
4.訓練網絡並更新網絡參數
5.測試網絡

import torchvision as tv            #里面含有許多數據集
import torch
import torchvision.transforms as transforms    #實現圖片變換處理的包
from torchvision.transforms import ToPILImage

#使用torchvision加載並預處理CIFAR10數據集
show = ToPILImage()         #可以把Tensor轉成Image,方便進行可視化
transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize(mean = (0.5,0.5,0.5),std = (0.5,0.5,0.5))])#把數據變為tensor並且歸一化range [0, 255] -> [0.0,1.0]
trainset = tv.datasets.CIFAR10(root='data1/',train = True,download=True,transform=transform)
trainloader = torch.utils.data.DataLoader(trainset,batch_size=4,shuffle=True,num_workers=0)
testset = tv.datasets.CIFAR10('data1/',train=False,download=True,transform=transform)
testloader = torch.utils.data.DataLoader(testset,batch_size=4,shuffle=True,num_workers=0)
classes = ('plane','car','bird','cat','deer','dog','frog','horse','ship','truck')
(data,label) = trainset[100]
print(classes[label])#輸出ship
show((data+1)/2).resize((100,100))
dataiter = iter(trainloader)
images, labels = dataiter.next()
print(' '.join('%11s'%classes[labels[j]] for j in range(4)))
show(tv.utils.make_grid((images+1)/2)).resize((400,100))#make_grid的作用是將若干幅圖像拼成一幅圖像

#定義網絡
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.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 = F.max_pool2d(F.relu(self.conv1(x)),(2,2))
        x = F.max_pool2d(F.relu(self.conv2(x)),2)
        x = x.view(x.size()[0],-1)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return  x

net = Net()
print(net)

#定義損失函數和優化器
from torch import optim
criterion  = nn.CrossEntropyLoss()#定義交叉熵損失函數
optimizer = optim.SGD(net.parameters(),lr = 0.001,momentum=0.9)

#訓練網絡
from torch.autograd  import Variable
for epoch in range(2):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):#enumerate將其組成一個索引序列，利用它可以同時獲得索引和值,enumerate還可以接收第二個參數，用於指定索引起始值
        inputs, labels = data
        inputs, labels = Variable(inputs), Variable(labels)
        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---------")
dataiter = iter(testloader)
images, labels = dataiter.next()
print('實際的label: ',' '.join('%08s'%classes[labels[j]] for j in range(4)))
show(tv.utils.make_grid(images/2 - 0.5)).resize((400,100))#？？？？？
outputs = net(Variable(images))
_, predicted = torch.max(outputs.data,1)#返回最大值和其索引
print('預測結果:',' '.join('%5s'%classes[predicted[j]] for j in range(4)))
correct = 0
total = 0
for data in testloader:
    images, labels = data
    outputs = net(Variable(images))
    _, predicted = torch.max(outputs.data, 1)
    total +=labels.size(0)
    correct +=(predicted == labels).sum()
print('10000張測試集中的准確率為: %d %%'%(100*correct/total))
if torch.cuda.is_available():
    net.cuda()
    images = images.cuda()
    labels = labels.cuda()
    output = net(Variable(images))
    loss = criterion(output, Variable(labels))

學習率太大會很難逼近最優值，所以要注意在數據集小的情況下學習率盡量小一些，epoch盡量大一些。

這個例子是陳雲的深度學習pytorch框架書上的一個demo，運行該代碼需要注意的是數據集的下載問題，因為運行程序很可能數據集下載很慢或者直接下載失敗，因此推薦使用迅雷根據指定網址直接下載，半分鍾就可以下載好。