PART 1
定义网络结构 ResNet-18
def conv3x3(in_planes, out_planes, stride=1):
"3x3 convolution with padding"
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=1, bias=False)
class BasicBlock(nn.Module):
expansion = 1
# inplanes其实就是channel,叫法不同
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)
# 把shortcut那的channel的维度统一
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=10):
self.inplanes = 64
super(ResNet, self).__init__()
self.conv1 = nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3, # 因为mnist为(1,28,28)灰度图,因此输入通道数为1
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 主要用来处理H(x)=F(x)+x中F(x)和xchannel维度不匹配问题
downsample = None
# self.inplanes为上个box_block的输出channel,planes为当前box_block块的输入channel
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):
"""Constructs a ResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
# [2, 2, 2, 2]和结构图[]X2是对应的
model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
return model
PART 2
定义一个钩子函数。这方法用于打印获取到的feature的形状。
def hook(module, inputdata, output):
print(output.data.shape)
PART 3 打印网络每层的name
这里打印的是每层的参数的名字 我们使用每层的名字即可。
如 conv1.weight 是第一个卷积层的权重名字。这层的层名就是conv1。
Layer1中包含2个residual 模块 分别对应索引0和1。
PART 4
使用pytorch中 nn.module里的 register_forward_hook() 来获取网络forward时的feature。
获取网络不同层的feature并传到hook函数中打印feature的形状。
记得把定义的钩子删除。
也可以打印网络的feature 修改hook函数即可 。