Resnet代码实现+为什么使用全局平均池化
1.ResNet直接使用stride=2的卷积做下采样，并且用global average pool层替换了全连接层。
GAP的真正意义是:对整个网路在结构上做正则化防止过拟合。但是值得我们注意的是，使用gap可能会造成收敛速度减慢。用一个GAP将N个feature map降维成1*N大小的feature map,再用class个1*1卷积核将1*N的feature map卷成1*class的向量。
①摘取重点于：为什么使用全局平均池化。
在卷积神经网络的初期，卷积层通过池化层（一般是MaxPooling）后总是要一个或n个全连接层，全连接网络可以使feature map的维度减少，进而输入到softmax分类。其特征就是全连接层的参数超多，模型本身非常臃肿，又会造成过拟合。（现在已经很少大量使用fc层），用pooling来代替全连接。就解决了之前的问题：要不要在fc层使用dropout。使用AVP就不要了。
（作者自己思考的部分，不知对错）全局平均池化层代替全连接层虽然有好处，但是不利于迁移学习。因为参数较为“固化”在卷积的诸层网络中。增加新的分类，那就意味着相当数量的卷积特征要做调整。而全连接层模型则可以更好的迁移学习，因为它的参数很大一部分调整在全连接层，迁移的时候卷积层可能也会调整，但是相对来讲要小的多了。
再对比：论文R-FCN(全卷积+位置敏感型“Score Map”) (目标检测)(two-stage)(深度学习)(NIPS 2016)中的Position-sensitive score map
②小例子1 ③④
2.ResNet的一个重要设计原则是：当feature map大小降低一半时，feature map的数量增加一倍，这保持了网络层的复杂度。
那么我是否也要一致呢？
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