首先看张核心的resnet层次结构图(图1)，它诠释了resnet18-152是如何搭建的，其中resnet18和resnet34结构类似，而resnet50-resnet152结构类似。下面先看resnet18的源码
图1
resnet18
首先是models.resnet18函数的调用
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)
if pretrained: #加载模型权重
model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
return model- 这里涉及到了一个BasicBlock类(resnet18和34)，这样的一个结构我们称为一个block，因为在block内部的conv都使用了padding，输入的in_img_size和out_img_size都是56x56，在图2右边的shortcut只需要改变输入的channel的大小，输入bloack的输入tensor和输出tensor就可以相加(详细内容)
图2
事实上图2是Bottleneck类(用于resnet50-152，稍后分析)，其和BasicBlock差不多，图3为图2的精简版(ps:可以把下图视为为一个box_block，即多个block叠加在一起，x3说明有3个上图一样的结构串起来)：
- 图3
BasicBlock类，可以对比结构图中的resnet18和resnet34，类中expansion =1，其表示box_block中最后一个block的channel比上第一个block的channel，即：
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)
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 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)
def resnet152(pretrained=False, **kwargs):
"""Constructs a ResNet-152 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True)
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)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
RuntimeError: size mismatch, m1: [1 x 8192], m2: [2048 x 1000] at c:\miniconda2\conda-bld\pytorch-cpu_1519449358620\work\torch\lib\th\generic/THTensorMath.c:1434- 1
- 1
首先我们看下，resnet在哪些地方改变了输出图像的大小
conv和pool层的输出大小都可以根据下面公式计算得出
但是resnet里面的卷积层太多了，就resnet152的height而言，其最后avgpool后的大小为,因此修改源码把图像的height和width传递进去，从而兼容非224的图片大小：
self.avgpool = nn.AvgPool2d(7, stride=1)
f = lambda x:math.ceil(x /32 - 7 + 1)
self.fc = nn.Linear(512 * block.expansion * f(w) * f(h), num_classes) #block.expansion=4- 也可以在外面替换跳最后一个fc层，这里的2048即本文图1中resnet152对应的最后layer的输出channel，若是resnet18或resnet34则为512
model_ft = models.resnet152(pretrained=True)
f = lambda x:math.ceil(x /32 - 7 + 1)
model_ft.fc = nn.Linear(f(target_w) * f(target_h) * 2048, nb_classes)- 还有另外一种暴力的方法，就是不管卷积层的输出大小，取其平均值做为输出，比如：
self.main = torchvision.models.resnet152(pretrained)
self.main.avgpool = nn.AdaptiveAvgPool2d((1, 1))本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
