一、VGG16的結構層次

VGG16總共有16層，13個卷積層和3個全連接層，第一次經過64個卷積核的兩次卷積后，采用一次pooling，第二次經過兩次128個卷積核卷積后，采用pooling；再經過3次256個卷積核卷積后。采用pooling，再重復兩次三個512個卷積核卷積后，再pooling，最后經過三次全連接。

1、附上官方的vgg16網絡結構圖:

• conv3-64的全稱就是convolution kernel_size=3, the number of kernel=64，也就是說，這一層是卷積層，卷積核尺寸是3x3xn(n代表channels，是輸入該層圖像數據的通道數)，該卷積層有64個卷積核實施卷積操作。
• FC4096全稱是Fully Connected 4096，是輸出層連接4096個神經元的全連接層。
• maxpool就是最大池化操作。最大值池化的窗口尺寸是2×2，步長stride=2

2、 VGG模型所需的內存容量：

?二、模型搭建

VGG16實現，基于CIFAR-10數據集

• CIFAR-10：該數據集共有60000張彩色圖像，這些圖像是32*32，分為10個類，每類6000張圖，50000 training images and 10000 test images.
• CIFAR-10：CIFAR-10 and CIFAR-100 datasets (toronto.edu)

1、數據加載

#加載數據 transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]) #訓練集 trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform) trainloader = torch.utils.data.DataLoader(trainset, batch_size=100, shuffle=True) #測試集 testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform) testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False) classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

2、VGG16網絡實現

class Vgg16_net(nn.Module):def __init__(self):super(Vgg16_net, self).__init__()self.layer1=nn.Sequential(nn.Conv2d(in_channels=3,out_channels=64,kernel_size=3,stride=1,padding=1), #(32-3+2)/1+1=32 32*32*64nn.BatchNorm2d(64),#inplace-選擇是否進行覆蓋運算#意思是是否將計算得到的值覆蓋之前的值，比如nn.ReLU(inplace=True),#意思就是對從上層網絡Conv2d中傳遞下來的tensor直接進行修改，#這樣能夠節省運算內存，不用多存儲其他變量nn.Conv2d(in_channels=64,out_channels=64,kernel_size=3,stride=1,padding=1), #(32-3+2)/1+1=32 32*32*64#Batch Normalization強行將數據拉回到均值為0，方差為1的正太分布上，# 一方面使得數據分布一致，另一方面避免梯度消失。nn.BatchNorm2d(64),nn.ReLU(inplace=True),nn.MaxPool2d(kernel_size=2,stride=2) #(32-2)/2+1=16 16*16*64)self.layer2=nn.Sequential(nn.Conv2d(in_channels=64,out_channels=128,kernel_size=3,stride=1,padding=1), #(16-3+2)/1+1=16 16*16*128nn.BatchNorm2d(128),nn.ReLU(inplace=True),nn.Conv2d(in_channels=128,out_channels=128,kernel_size=3,stride=1,padding=1), #(16-3+2)/1+1=16 16*16*128nn.BatchNorm2d(128),nn.ReLU(inplace=True),nn.MaxPool2d(2,2) #(16-2)/2+1=8 8*8*128)self.layer3=nn.Sequential(nn.Conv2d(in_channels=128,out_channels=256,kernel_size=3,stride=1,padding=1), #(8-3+2)/1+1=8 8*8*256nn.BatchNorm2d(256),nn.ReLU(inplace=True),nn.Conv2d(in_channels=256,out_channels=256,kernel_size=3,stride=1,padding=1), #(8-3+2)/1+1=8 8*8*256nn.BatchNorm2d(256),nn.ReLU(inplace=True),nn.Conv2d(in_channels=256,out_channels=256,kernel_size=3,stride=1,padding=1), #(8-3+2)/1+1=8 8*8*256nn.BatchNorm2d(256),nn.ReLU(inplace=True),nn.MaxPool2d(2,2) #(8-2)/2+1=4 4*4*256)self.layer4=nn.Sequential(nn.Conv2d(in_channels=256,out_channels=512,kernel_size=3,stride=1,padding=1), #(4-3+2)/1+1=4 4*4*512nn.BatchNorm2d(512),nn.ReLU(inplace=True),nn.Conv2d(in_channels=512,out_channels=512,kernel_size=3,stride=1,padding=1), #(4-3+2)/1+1=4 4*4*512nn.BatchNorm2d(512),nn.ReLU(inplace=True),nn.Conv2d(in_channels=512,out_channels=512,kernel_size=3,stride=1,padding=1), #(4-3+2)/1+1=4 4*4*512nn.BatchNorm2d(512),nn.ReLU(inplace=True),nn.MaxPool2d(2,2) #(4-2)/2+1=2 2*2*512)self.layer5=nn.Sequential(nn.Conv2d(in_channels=512,out_channels=512,kernel_size=3,stride=1,padding=1), #(2-3+2)/1+1=2 2*2*512nn.BatchNorm2d(512),nn.ReLU(inplace=True),nn.Conv2d(in_channels=512,out_channels=512,kernel_size=3,stride=1,padding=1), #(2-3+2)/1+1=2 2*2*512nn.BatchNorm2d(512),nn.ReLU(inplace=True),nn.Conv2d(in_channels=512,out_channels=512,kernel_size=3,stride=1,padding=1), #(2-3+2)/1+1=2 2*2*512nn.BatchNorm2d(512),nn.ReLU(inplace=True),nn.MaxPool2d(2,2) #(2-2)/2+1=1 1*1*512)self.conv=nn.Sequential(self.layer1,self.layer2,self.layer3,self.layer4,self.layer5)self.fc=nn.Sequential(#y=xA^T+b x是輸入,A是權值,b是偏執,y是輸出#nn.Liner(in_features,out_features,bias)#in_features:輸入x的列數 輸入數據:[batchsize,in_features]#out_freatures:線性變換后輸出的y的列數,輸出數據的大小是:[batchsize,out_features]#bias: bool 默認為True#線性變換不改變輸入矩陣x的行數,僅改變列數nn.Linear(512,512),nn.ReLU(inplace=True),nn.Dropout(0.5),nn.Linear(512,256),nn.ReLU(inplace=True),nn.Dropout(0.5),nn.Linear(256,10))def forward(self,x):x=self.conv(x)#這里-1表示一個不確定的數，就是你如果不確定你想要reshape成幾行，但是你很肯定要reshape成512列# 那不確定的地方就可以寫成-1#如果出現x.size(0)表示的是batchsize的值# x=x.view(x.size(0),-1)x = x.view(-1, 512)x=self.fc(x)return x

3、模型訓練

mini-batch設置為100，每加載50個mini-batch，統計一次數據（5000張圖）

''' 模型訓練 ''' def net_train():epoch = 10 # 訓練次數learning_rate = 1e-4 # 學習率net = Vgg16_net()criterion = nn.CrossEntropyLoss()optimizer = optim.Adam(net.parameters(), lr=learning_rate)print('start Training.......')print("print msg : 50 mini-batches per time")for epoch in range(epoch): # 迭代running_loss = 0.0running_acc = 0.0print('*' * 25, 'epoch {}'.format(epoch + 1), '*' * 25, "——> ")for i, data in enumerate(trainloader, 0):inputs, labels = data#print("i: {}, inputs: {}, labels: {}".format(i, len(inputs), len(labels)))# 向前傳播out = net(inputs)loss = criterion(out, labels)running_loss += loss.item() * labels.size(0)_, pred = torch.max(out, 1) # 預測最大值所在的位置標簽num_correct = (pred == labels).sum()# 初始化梯度optimizer.zero_grad()outputs = net(inputs)loss = criterion(outputs, labels)loss.backward()optimizer.step()# 打印loss 和 accrunning_acc += num_correct.item()running_loss += loss.item()if i % 50 == 49: # print every 5000 mini-batchesprint('[%d, %5d] loss: %.5f Acc：%.5f' %(epoch + 1, i + 1, running_loss / 5000, running_acc / 5000))running_loss = 0.0running_acc = 0.0print('Finished Training')return net

4、模型測試

''' 模型測試 ''' def net_test(model):model.eval() # 模型評估criterion = nn.CrossEntropyLoss()eval_loss = 0eval_acc = 0for data in testloader: # 測試模型img, label = dataout = model(img)loss = criterion(out, label)eval_loss += loss.item() * label.size(0)_, pred = torch.max(out, 1)num_correct = (pred == label).sum()eval_acc += num_correct.item()print('Test Loss: {:.6f}, Acc: {:.6f}'.format(eval_loss / (len(testset)), eval_acc / (len(testset))))

總結

以上是生活随笔為你收集整理的[VGG16]——网络结构介绍及搭建(PyTorch)的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。