VGG

AlexNet在Lenet的基礎上增加了幾個卷積層,改變了卷積核大小,每一層輸出通道數目等,並且取得了很好的效果.但是並沒有提出一個簡單有效的思路.
VGG做到了這一點,提出了可以通過重複使⽤簡單的基礎塊來構建深度學習模型的思路.

論文地址:https://arxiv.org/abs/1409.1556

vgg的結構如下所示:

上圖給出了不同層數的vgg的結構.也就是常說的vgg16,vgg19等等.

VGG BLOCK

vgg的設計思路是,通過不斷堆疊3x3的卷積核,不斷加深模型深度.vgg net證明了加深模型深度對提高模型的學習能力是一個很有效的手段.

看上圖就能發現,連續的2個3x3卷積,感受野和一個5x5卷積是一樣的,但是前者有兩次非線性變換,後者只有一次!,這就是連續堆疊小卷積核能提高

vgg的基礎組成模組,每一個卷積層都由n個3x3卷積後面接2x2的最大池化.池化層的步幅為2.從而卷積層卷積後,寬高不變,池化後,寬高減半.
我們可以有以下程式碼:

def make_layers(in_channels,cfg):
    layers = []
    previous_channel = in_channels #上一層的輸出的channel數量
    for v in cfg:
        if v == 'M':
            layers.append(nn.MaxPool2d(kernel_size=2,stride=2))
        else:
            layers.append(nn.Conv2d(previous_channel,v,kernel_size=3,padding=1))
            layers.append(nn.ReLU())

            previous_channel = v

    conv = nn.Sequential(*layers)
    return conv


cfgs = {
    'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'B': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
    'E': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}
 

cfgs定義了不同的vgg模型的結構,比如'A'代表vgg11．　數字代表卷積後的channel數. 'M'代表Maxpool

我們可以給出模型定義

class VGG(nn.Module):
    def __init__(self,input_channels,cfg,num_classes=10, init_weights=True):
        super(VGG, self).__init__()
        self.conv = make_layers(input_channels,cfg) # torch.Size([1, 512, 7, 7])
        self.fc = nn.Sequential(
            nn.Linear(512*7*7,4096),
            nn.ReLU(),
            nn.Linear(4096,4096),
            nn.ReLU(),
            nn.Linear(4096,num_classes)
        )
    
    def forward(self, img):
        feature = self.conv(img)
        output = self.fc(feature.view(img.shape[0], -1))
        return output
 

卷積層的輸出可由以下測試程式碼得出

# conv = make_layers(1,cfgs['A'])
# X = torch.randn((1,1,224,224))
# out = conv(X)
# #print(out.shape)

載入資料

batch_size,num_workers=4,4
train_iter,test_iter = learntorch_utils.load_data(batch_size,num_workers,resize=224)

這裡batch_size調到8我的視訊記憶體就不夠了...

定義模型

net = VGG(1,cfgs['A']).cuda()

定義損失函式

loss = nn.CrossEntropyLoss()

定義優化器　

opt = torch.optim.Adam(net.parameters(),lr=0.001)

定義評估函式

def test():
    acc_sum = 0
    batch = 0
    for X,y in test_iter:
        X,y = X.cuda(),y.cuda()
        y_hat = net(X)
        acc_sum += (y_hat.argmax(dim=1) == y).float().sum().item()
        batch += 1
    #print('acc_sum %d,batch %d' % (acc_sum,batch))

    return 1.0*acc_sum/(batch*batch_size)

訓練

num_epochs = 3
def train():
    for epoch in range(num_epochs):
        train_l_sum,batch,acc_sum = 0,0,0
        start = time.time()
        for X,y in train_iter:
            # start_batch_begin = time.time()
            X,y = X.cuda(),y.cuda()
            y_hat = net(X)
            acc_sum += (y_hat.argmax(dim=1) == y).float().sum().item()

            l = loss(y_hat,y)
            opt.zero_grad()
            l.backward()

            opt.step()
            train_l_sum += l.item()

            batch += 1

            mean_loss = train_l_sum/(batch*batch_size) #計算平均到每張圖片的loss
            start_batch_end = time.time()
            time_batch = start_batch_end - start

            print('epoch %d,batch %d,train_loss %.3f,time %.3f' % 
                (epoch,batch,mean_loss,time_batch))

        print('***************************************')
        mean_loss = train_l_sum/(batch*batch_size) #計算平均到每張圖片的loss
        train_acc = acc_sum/(batch*batch_size)     #計算訓練準確率
        test_acc = test()                           #計算測試準確率
        end = time.time()
        time_per_epoch =  end - start
        print('epoch %d,train_loss %f,train_acc %f,test_acc %f,time %f' % 
                (epoch + 1,mean_loss,train_acc,test_acc,time_per_epoch))

train()

4G的GTX 1050顯示卡,訓練一個epoch大概一個多小時.
完整程式碼:https://github.com/sdu2011/learn_pyto