深层网络的问题
网络越深，能获取的信息越多，特征也越丰富。但是根据实验表明，随着网络的加深，优化效果反而越差，测试数据和训练数据的准确率反而降低了。这是由于网络的加深会造成梯度爆炸和梯度消失的问题。
针对这种现象已经有了解决的方法：对输入数据和中间层的数据进行归一化操作，这种方法可以保证网络在反向传播中采用随机梯度下降（SGD），从而让网络达到收敛。但是，这个方法仅对几十层的网络有用，当网络再往深处走的时候，这种方法就无用武之地了。
残差模块
这有点类似与电路中的“短路”，所以是一种短路连接（shortcut connection），该残差块也被称为shortcut。它的原理是：对于一个堆积层结构（几层堆积而成）当输入为 x时，其学习到的特征记为 H(x) ，现在我们希望其可以学习到残差 F(x)=H(x)-x ，这样其实原始的学习特征是 F(x)+x 。之所以这样是因为残差学习相比原始特征直接学习更容易。当残差为 0 时，此时堆积层仅仅做了恒等映射，至少网络性能不会下降，实际上残差不会为 0，这也会使得堆积层在输入特征基础上学习到新的特征，从而拥有更好的性能。
总的来看，该层的神经网络可以不用学习整个的输出，而是学习上一个网络输出的残差，因此ResNet又叫做残差网络。
也就是说在使用残差模块后，突出了微小的变化！！解决了梯度消失的问题！所以关键其实就是这个！！！
Resnet实现
import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
def conv3x3(in_planes, out_planes, stride=1):
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=1, bias=False)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, layers, num_classes=1000):
self.inplanes = 64
super(ResNet, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
self.avgpool = nn.AvgPool2d(7, stride=1)
self.fc = nn.Linear(512 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
return x
def resnet18(pretrained=False, **kwargs):
trained (bool): If True, returns a model pre-trained on ImageNet
model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
return model
