def resnet18(pretrained=False, **kwargs): """Constructs a ResNet-18 model. Args: pretrained (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
定义Resnet34
def resnet34(pretrained=False, **kwargs): """Constructs a ResNet-34 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet """ model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs) if pretrained: model.load_state_dict(model_zoo.load_url(model_urls['resnet34'])) return model
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
下面我们分别看看这两个过程:
网络的forward过程
def forward(self, x): #x代表输入 x = self.conv1(x) #进过卷积层1 x = self.bn1(x) #bn1层 x = self.relu(x) #relu激活 x = self.maxpool(x) #最大池化 x = self.layer1(x) #卷积块1 x = self.layer2(x) #卷积块2 x = self.layer3(x) #卷积块3 x = self.layer4(x) #卷积块4 x = self.avgpool(x) #平均池化 x = x.view(x.size(0), -1) #二维变成变成一维向量 x = self.fc(x) #全连接层 return x
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
我画个流程图来表示一下
画的比较丑,不过基本意思在里面了,
根据论文的描述,x是否需要下采样由x与out是否大小一样决定,
假如进过conv2和bn2后的结果我们称之为 P
假设x的大小为wHchannel1
如果P的大小也是wHchannel1
则无需下采样 out = relu(P + X) out的大小为W * H *(channel1+channel2),
如果P的大小是W/2 * H/2 * channel
则X需要下采样后才能与P相加, out = relu(P+ X下采样) out的大小为W/2 * H/2 * (channel1+channel2)