使用Pytorch對數據集CIFAR-10分類處理

使用Pytorch對數據集CIFAR-10進行分類，主要是以下幾個步驟：

1. 下載並預處理數據集
2. 定義網絡結構
3. 定義損失函數和優化器
4. 訓練網絡並更新參數
5. 測試網絡效果

#數據加載和預處理
#使用CIFAR-10數據進行分類實驗
import torch as t
import torchvision as tv
import torchvision.transforms as transforms
from torchvision.transforms import ToPILImage
show = ToPILImage() # 可以把Tensor轉成Image，方便可視化

#定義對數據的預處理
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5)),  #歸一化
])

#訓練集
trainset = tv.datasets.CIFAR10(
    root = './data/',
    train = True,
    download = True,
    transform = transform
)

trainloader = t.utils.data.DataLoader(
    trainset,
    batch_size = 4,
    shuffle = True,
    num_workers = 2,
)

#測試集
testset = tv.datasets.CIFAR10(
    root = './data/',
    train = False,
    download = True,
    transform = transform,
)
testloader = t.utils.data.DataLoader(
    testset,
    batch_size = 4,
    shuffle = False,
    num_workers = 2,
)

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

 初次下載需要一些時間，運行結束後，顯示如下：

import torch.nn as nn
import torch.nn.functional as F
import time
start = time.time()#計時
#定義網絡結構
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)
        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)

 顯示net結構如下：

#定義優化和損失
loss_func = nn.CrossEntropyLoss()  #交叉熵損失函數
optimizer = t.optim.SGD(net.parameters(),lr = 0.001,momentum = 0.9)

#訓練網絡
for epoch in range(2):
    running_loss = 0
    for i,data in enumerate(trainloader,0):
        inputs,labels = data
       
        outputs = net(inputs)
        loss = loss_func(outputs,labels)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        running_loss +=loss.item()
        if i%2000 ==1999:
            print('epoch:',epoch+1,'|i:',i+1,'|loss:%.3f'%(running_loss/2000))
            running_loss = 0.0
end = time.time()
time_using = end - start
print('finish training')
print('time:',time_using)

 結果如下：

下一步進行使用測試集進行網絡測試：

#測試網絡
correct = 0 #定義的預測正確的圖片數
total = 0#總共圖片個數
with t.no_grad():
    for data in testloader:
        images,labels = data
        outputs = net(images)
        _,predict = t.max(outputs,1)
        total += labels.size(0)
        correct += (predict == labels).sum()
print('測試集中的準確率爲：%d%%'%(100*correct/total))

結果如下：

 

簡單的網絡訓練確實要比10%的比例高一點：） 

在GPU中訓練：

#在GPU中訓練
device = t.device('cuda:0' if t.cuda.is_available() else 'cpu')

net.to(device)
images = images.to(device)
labels = labels.to(device)

output = net(images)
loss = loss_func(output,labels)

loss