resnet50特征图分辨率和通道数的变化
resnet50构建的核心代码如下，注释内容说明了特征图分辨率和通道数的变化情况
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) #特征图分辨率降低为1/2，通道数从3升为64
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)#特征图分辨率降低为1/4，通道数仍然为64
self.layer1 = self._make_layer(block, 64, layers[0]) #stride为1，不改变分辨率，依然为1/4，通道数从64升为64*4=256
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)#stride为2，特征图分辨率降低为1/8，通道数从256升为128*4=512
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)#stride为2，特征图分辨率降低为1/16，通道数从512升为256*4=1024
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)#stride为2，特征图分辨率降低为1/32，通道数从512升为256*4=2048
一般使用resnet50输出的4个特征图。4个特征图的分辨率依次为原始图片的1/4, 1/8, 1/16, 1/32，通道数依次为256，512，1024，2048。
def forward(self, x):
x = self.conv1(x) #特征图分辨率降低为1/2,通道数变为64
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)#特征图分辨率降低为1/4,通道数仍然为64
x1 = self.layer1(x)#特征图分辨率仍然为1/4,通道数变为为256
x2 = self.layer2(x1)#特征图分辨率变为1/8,通道数变为为512
x3 = self.layer3(x2)#特征图分辨率变为1/16,通道数变为为1024
x4 = self.layer4(x3)#特征图分辨率变为1/32,通道数变为为2048
return [x4, x3, x2, x1]
完整代码如下
import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
'resnet152']
model_urls = {
'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
}
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
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 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)
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)
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)
x1 = self.layer1(x)
x2 = self.layer2(x1)
x3 = self.layer3(x2)
x4 = self.layer4(x3)
return [x4, x3, x2, x1]
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:
from collections import OrderedDict
state_dict = model.state_dict()
pretrained_state_dict = model_zoo.load_url(model_urls['resnet18'])
for k, v in pretrained_state_dict.items():
if k not in state_dict:
continue
state_dict[k] = v
model.load_state_dict(state_dict)
return model
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:
from collections import OrderedDict
state_dict = model.state_dict()
pretrained_state_dict = model_zoo.load_url(model_urls['resnet34'])
for k, v in pretrained_state_dict.items():
if k not in state_dict:
continue
state_dict[k] = v
model.load_state_dict(state_dict)
return model
def resnet50(pretrained=False, **kwargs):
"""Constructs a ResNet-50 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
if pretrained:
print('Initialize with pre-trained ResNet')
from collections import OrderedDict
state_dict = model.state_dict()
pretrained_state_dict = model_zoo.load_url(model_urls['resnet50'])
for k, v in pretrained_state_dict.items():
if k not in state_dict:
continue
state_dict[k] = v
print('successfully load '+str(len(state_dict.keys()))+' keys')
model.load_state_dict(state_dict)
return model
def resnet101(pretrained=False, **kwargs):
"""Constructs a ResNet-101 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
if pretrained:
print('Initialize with pre-trained ResNet')
from collections import OrderedDict
state_dict = model.state_dict()
pretrained_state_dict = model_zoo.load_url(model_urls['resnet101'])
for k, v in pretrained_state_dict.items():
if k not in state_dict:
continue
state_dict[k] = v
print('successfully load '+str(len(state_dict.keys()))+' keys')
model.load_state_dict(state_dict)
return model
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:
from collections import OrderedDict
state_dict = model.state_dict()
pretrained_state_dict = model_zoo.load_url(model_urls['resnet152'])
for k, v in pretrained_state_dict.items():
if k not in state_dict:
continue
state_dict[k] = v
model.load_state_dict(state_dict)
return model
if __name__=='__main__':
import torch
model = resnet50()
input = torch.rand([4,3,256,192])
print(input.shape)
output = model(input)
print(type(output))
print(len(output))
print(output[0].shape)
print(output[1].shape)
print(output[2].shape)
print(output[3].shape)