現在重新稍微系統的介紹一下ResNet網絡結構。 ResNet結構首先通過一個卷積層然后有一個池化層，然后通過一系列的殘差結構，最后再通過一個平均池化下采樣操作，以及一個全連接層的得到了一個輸出。ResNet網絡可以達到很深的層數的原因就是不斷的堆疊殘差結構而來的。
當層數過多的時候，假設每一層的誤差梯度都是一個小于1的數值，當進行方向傳播的過程中，每向前傳播一層，都要乘以一個小于1的誤差梯度，當網絡越來越深時，所成的小于1的系數也就越來越多，此時梯度便越趨近于0，這樣梯度便會越來越小。這便會造成梯度消失的現象。
當解決了梯度消失或者梯度爆炸的問題之后，其實網絡的效果可能還是不盡如意，還可能有退化問題。為此，ResNet提出了殘差結構來解決這個退化問題。 也正是因為有這個殘差的結構，所以才可以搭建這么深的網絡。
作圖是針對ResNet-18/34層淺層網絡的結構，右圖是ResNet-50/101/152層深層網絡的結構，其中注意：主分支與shortcut 的輸出特征矩陣shape。
需要注意，有些殘差結構的ShortCut是實線，而有的是虛線，這兩者是不同的。對于左圖來說，ShortCut是實線，這表明輸入與輸出的shape是一樣的，所以可以直接的進行相加。而對于右圖來說，其輸入的shape與輸出的shape是不一樣的，這時候需要調整步長stribe與kernel size來使得兩條路（主分支與捷徑分支）所處理好的shape是一模一樣的。
右側虛線殘差結構的主分支上、第一個1x1卷積層的步距是2，第二個3x3卷積層的步距是1.
對于第一個大模塊的第一個殘差結構，其第二個3x3的卷積中，步長是1的，而其他的三個大模塊的步長均為2.
在每一個大模塊的維度變換中，主要是第一個殘差結構使得shape減半，而模塊中其他的殘差結構都是沒有改變shape的。也真因為沒有改變shape，所以這些殘差結構才可以直接的通過實線進行相加。
Batch Normalization是google團隊在2015年論文《Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift》提出的。通過該方法能夠加速網絡的收斂并提升準確率。
import torch
import torch.nn as nn
# 分類數目
num_class = 5
# 各層數目
resnet18_params = [2, 2, 2, 2]
resnet34_params = [3, 4, 6, 3]
resnet50_params = [3, 4, 6, 3]
resnet101_params = [3, 4, 23, 3]
resnet152_params = [3, 8, 36, 3]
# 定義Conv1層
def Conv1(in_planes, places, stride=2):
return nn.Sequential(
nn.Conv2d(in_channels=in_planes,out_channels=places,kernel_size=7,stride=stride,padding=3, bias=False),
nn.BatchNorm2d(places),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
)
# 淺層的殘差結構
class BasicBlock(nn.Module):
def __init__(self,in_places,places, stride=1,downsampling=False, expansion = 1):
super(BasicBlock,self).__init__()
self.expansion = expansion
self.downsampling = downsampling
# torch.Size([1, 64, 56, 56]), stride = 1
# torch.Size([1, 128, 28, 28]), stride = 2
# torch.Size([1, 256, 14, 14]), stride = 2
# torch.Size([1, 512, 7, 7]), stride = 2
self.basicblock = nn.Sequential(
nn.Conv2d(in_channels=in_places, out_channels=places, kernel_size=3, stride=stride, padding=1, bias=False),
nn.BatchNorm2d(places),
nn.ReLU(inplace=True),
nn.Conv2d(in_channels=places, out_channels=places, kernel_size=3, stride=1, padding=1, bias=False),
nn.BatchNorm2d(places * self.expansion),
)
# torch.Size([1, 64, 56, 56])
# torch.Size([1, 128, 28, 28])
# torch.Size([1, 256, 14, 14])
# torch.Size([1, 512, 7, 7])
# 每個大模塊的第一個殘差結構需要改變步長
if self.downsampling:
self.downsample = nn.Sequential(
nn.Conv2d(in_channels=in_places, out_channels=places*self.expansion, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(places*self.expansion)
)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
# 實線分支
residual = x
out = self.basicblock(x)
# 虛線分支
if self.downsampling:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
# 深層的殘差結構
class Bottleneck(nn.Module):
# 注意:默認 downsampling=False
def __init__(self,in_places,places, stride=1,downsampling=False, expansion = 4):
super(Bottleneck,self).__init__()
self.expansion = expansion
self.downsampling = downsampling
self.bottleneck = nn.Sequential(
# torch.Size([1, 64, 56, 56])，stride=1
# torch.Size([1, 128, 56, 56])，stride=1
# torch.Size([1, 256, 28, 28]), stride=1
# torch.Size([1, 512, 14, 14]), stride=1
nn.Conv2d(in_channels=in_places,out_channels=places,kernel_size=1,stride=1, bias=False),
nn.BatchNorm2d(places),
nn.ReLU(inplace=True),
# torch.Size([1, 64, 56, 56])，stride=1
# torch.Size([1, 128, 28, 28]), stride=2
# torch.Size([1, 256, 14, 14]), stride=2
# torch.Size([1, 512, 7, 7]), stride=2
nn.Conv2d(in_channels=places, out_channels=places, kernel_size=3, stride=stride, padding=1, bias=False),
nn.BatchNorm2d(places),
nn.ReLU(inplace=True),
# torch.Size([1, 256, 56, 56])，stride=1
# torch.Size([1, 512, 28, 28]), stride=1
# torch.Size([1, 1024, 14, 14]), stride=1
# torch.Size([1, 2048, 7, 7]), stride=1
nn.Conv2d(in_channels=places, out_channels=places * self.expansion, kernel_size=1, stride=1, bias=False),
nn.BatchNorm2d(places * self.expansion),
)
# torch.Size([1, 256, 56, 56])
# torch.Size([1, 512, 28, 28])
# torch.Size([1, 1024, 14, 14])
# torch.Size([1, 2048, 7, 7])
if self.downsampling:
self.downsample = nn.Sequential(
nn.Conv2d(in_channels=in_places, out_channels=places*self.expansion, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(places*self.expansion)
)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
# 實線分支
residual = x
out = self.bottleneck(x)
# 虛線分支
if self.downsampling:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self,blocks, blockkinds, num_classes=num_class):
super(ResNet,self).__init__()
self.blockkinds = blockkinds
self.conv1 = Conv1(in_planes = 3, places= 64)
# 對應淺層網絡結構
if self.blockkinds == BasicBlock:
self.expansion = 1
# 64 -> 64
self.layer1 = self.make_layer(in_places=64, places=64, block=blocks[0], stride=1)
# 64 -> 128
self.layer2 = self.make_layer(in_places=64, places=128, block=blocks[1], stride=2)
# 128 -> 256
self.layer3 = self.make_layer(in_places=128, places=256, block=blocks[2], stride=2)
# 256 -> 512
self.layer4 = self.make_layer(in_places=256, places=512, block=blocks[3], stride=2)
self.fc = nn.Linear(512, num_classes)
# 對應深層網絡結構
if self.blockkinds == Bottleneck:
self.expansion = 4
# 64 -> 64
self.layer1 = self.make_layer(in_places = 64, places= 64, block=blocks[0], stride=1)
# 256 -> 128
self.layer2 = self.make_layer(in_places = 256,places=128, block=blocks[1], stride=2)
# 512 -> 256
self.layer3 = self.make_layer(in_places=512,places=256, block=blocks[2], stride=2)
# 1024 -> 512
self.layer4 = self.make_layer(in_places=1024,places=512, block=blocks[3], stride=2)
self.fc = nn.Linear(2048, num_classes)
self.avgpool = nn.AvgPool2d(7, stride=1)
# 初始化網絡結構
for m in self.modules():
if isinstance(m, nn.Conv2d):
# 采用了何凱明的初始化方法
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def make_layer(self, in_places, places, block, stride):
layers = []
# torch.Size([1, 64, 56, 56]) -> torch.Size([1, 256, 56, 56])， stride=1 故w，h不變
# torch.Size([1, 256, 56, 56]) -> torch.Size([1, 512, 28, 28])， stride=2 故w，h變
# torch.Size([1, 512, 28, 28]) -> torch.Size([1, 1024, 14, 14])，stride=2 故w，h變
# torch.Size([1, 1024, 14, 14]) -> torch.Size([1, 2048, 7, 7])， stride=2 故w，h變
# 此步需要通過虛線分支，downsampling=True
layers.append(self.blockkinds(in_places, places, stride, downsampling =True))
# torch.Size([1, 256, 56, 56]) -> torch.Size([1, 256, 56, 56])
# torch.Size([1, 512, 28, 28]) -> torch.Size([1, 512, 28, 28])
# torch.Size([1, 1024, 14, 14]) -> torch.Size([1, 1024, 14, 14])
# torch.Size([1, 2048, 7, 7]) -> torch.Size([1, 2048, 7, 7])
# print("places*self.expansion:", places*self.expansion)
# print("block:", block)
# 此步需要通過實線分支，downsampling=False， 每個大模塊的第一個殘差結構需要改變步長
for i in range(1, block):
layers.append(self.blockkinds(places*self.expansion, places))
return nn.Sequential(*layers)
def forward(self, x):
# conv1層
x = self.conv1(x) # torch.Size([1, 64, 56, 56])
# conv2_x層
x = self.layer1(x) # torch.Size([1, 256, 56, 56])
# conv3_x層
x = self.layer2(x) # torch.Size([1, 512, 28, 28])
# conv4_x層
x = self.layer3(x) # torch.Size([1, 1024, 14, 14])
# conv5_x層
x = self.layer4(x) # torch.Size([1, 2048, 7, 7])
x = self.avgpool(x) # torch.Size([1, 2048, 1, 1]) / torch.Size([1, 512])
x = x.view(x.size(0), -1) # torch.Size([1, 2048]) / torch.Size([1, 512])
x = self.fc(x) # torch.Size([1, 5])
return x
def ResNet18():
return ResNet(resnet18_params, BasicBlock)
def ResNet34():
return ResNet(resnet34_params, BasicBlock)
def ResNet50():
return ResNet(resnet50_params, Bottleneck)
def ResNet101():
return ResNet(resnet101_params, Bottleneck)
def ResNet152():
return ResNet(resnet152_params, Bottleneck)
if __name__=='__main__':
# model = torchvision.models.resnet50()
# 模型測試
# model = ResNet18()
# model = ResNet34()
# model = ResNet50()
# model = ResNet101()
model = ResNet152()
# print(model)
input = torch.randn(1, 3, 224, 224)
out = model(input)
print(out.shape)
