243 lines
9.2 KiB
Python
243 lines
9.2 KiB
Python
import torch
|
||
import torch.nn as nn
|
||
|
||
|
||
def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
|
||
"""3x3 convolution with padding"""
|
||
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
|
||
padding=dilation, groups=groups, bias=False, dilation=dilation)
|
||
|
||
|
||
def conv1x1(in_planes, out_planes, stride=1):
|
||
"""1x1 convolution"""
|
||
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
|
||
|
||
|
||
class Bottleneck(nn.Module):
|
||
# Bottleneck in torchvision places the stride for downsampling at 3x3 convolution(self.conv2)
|
||
# while original implementation places the stride at the first 1x1 convolution(self.conv1)
|
||
# according to "Deep residual learning for image recognition"https://arxiv.org/abs/1512.03385.
|
||
# This variant is also known as ResNet V1.5 and improves accuracy according to
|
||
# https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch.
|
||
|
||
expansion = 4
|
||
|
||
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
|
||
base_width=64, dilation=1, norm_layer=None):
|
||
super(Bottleneck, self).__init__()
|
||
if norm_layer is None:
|
||
norm_layer = nn.BatchNorm2d
|
||
width = int(planes * (base_width / 64.)) * groups
|
||
# Both self.conv2 and self.downsample layers downsample the input when stride != 1
|
||
self.conv1 = conv1x1(inplanes, width)
|
||
self.bn1 = norm_layer(width)
|
||
self.conv2 = conv3x3(width, width, stride, groups, dilation)
|
||
self.bn2 = norm_layer(width)
|
||
self.conv3 = conv1x1(width, planes * self.expansion)
|
||
self.bn3 = norm_layer(planes * self.expansion)
|
||
self.relu = nn.ReLU(inplace=True)
|
||
self.downsample = downsample
|
||
self.stride = stride
|
||
|
||
def forward(self, x):
|
||
identity = 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:
|
||
identity = self.downsample(x)
|
||
|
||
out += identity
|
||
out = self.relu(out)
|
||
|
||
return out
|
||
|
||
|
||
class ResNet(nn.Module):
|
||
|
||
def __init__(self, block, layers, num_classes=1000, zero_init_residual=False,
|
||
groups=1, width_per_group=64, replace_stride_with_dilation=None,
|
||
norm_layer=None):
|
||
super(ResNet, self).__init__()
|
||
if norm_layer is None:
|
||
norm_layer = nn.BatchNorm2d
|
||
self._norm_layer = norm_layer
|
||
|
||
self.inplanes = 64
|
||
self.dilation = 1
|
||
if replace_stride_with_dilation is None:
|
||
# each element in the tuple indicates if we should replace
|
||
# the 2x2 stride with a dilated convolution instead
|
||
replace_stride_with_dilation = [False, False, False]
|
||
if len(replace_stride_with_dilation) != 3:
|
||
raise ValueError("replace_stride_with_dilation should be None "
|
||
"or a 3-element tuple, got {}".format(replace_stride_with_dilation))
|
||
self.groups = groups
|
||
self.base_width = width_per_group
|
||
self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3,
|
||
bias=False)
|
||
self.bn1 = norm_layer(self.inplanes)
|
||
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,
|
||
dilate=replace_stride_with_dilation[0])
|
||
self.layer3 = self._make_layer(block, 256, layers[2], stride=2,
|
||
dilate=replace_stride_with_dilation[1])
|
||
self.layer4 = self._make_layer(block, 512, layers[3], stride=2,
|
||
dilate=replace_stride_with_dilation[2])
|
||
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
|
||
self.fc = nn.Linear(512 * block.expansion, num_classes)
|
||
|
||
for m in self.modules():
|
||
if isinstance(m, nn.Conv2d):
|
||
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
|
||
elif isinstance(m, nn.BatchNorm2d):
|
||
nn.init.constant_(m.weight, 1)
|
||
nn.init.constant_(m.bias, 0)
|
||
|
||
# Zero-initialize the last BN in each residual branch,
|
||
# so that the residual branch starts with zeros, and each residual block behaves like an identity.
|
||
# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
|
||
if zero_init_residual:
|
||
for m in self.modules():
|
||
if isinstance(m, Bottleneck):
|
||
nn.init.constant_(m.bn3.weight, 0)
|
||
|
||
def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
|
||
norm_layer = self._norm_layer
|
||
downsample = None
|
||
previous_dilation = self.dilation
|
||
if dilate:
|
||
self.dilation *= stride
|
||
stride = 1
|
||
if stride != 1 or self.inplanes != planes * block.expansion:
|
||
downsample = nn.Sequential(
|
||
conv1x1(self.inplanes, planes * block.expansion, stride),
|
||
norm_layer(planes * block.expansion),
|
||
)
|
||
|
||
layers = []
|
||
layers.append(block(self.inplanes, planes, stride, downsample, self.groups,
|
||
self.base_width, previous_dilation, norm_layer))
|
||
self.inplanes = planes * block.expansion
|
||
for _ in range(1, blocks):
|
||
layers.append(block(self.inplanes, planes, groups=self.groups,
|
||
base_width=self.base_width, dilation=self.dilation,
|
||
norm_layer=norm_layer))
|
||
|
||
return nn.Sequential(*layers)
|
||
|
||
def _forward_impl(self, x):
|
||
# See note [TorchScript super()]
|
||
x = self.conv1(x)
|
||
x = self.bn1(x)
|
||
x = self.relu(x)
|
||
x = self.maxpool(x) #1/4
|
||
|
||
x4 = self.layer1(x)
|
||
x8 = self.layer2(x)#8
|
||
x16 = self.layer3(x)#16
|
||
x32 = self.layer4(x)# 32
|
||
|
||
# x = self.avgpool(x)
|
||
# x = torch.flatten(x, 1)
|
||
# x = self.fc(x)
|
||
|
||
return x4,x8,x16,x32
|
||
|
||
def forward(self, x):
|
||
return self._forward_impl(x)
|
||
|
||
|
||
def _resnet(block, layers, **kwargs):
|
||
model = ResNet(block, layers, **kwargs)
|
||
return model
|
||
|
||
|
||
def resnet50(**kwargs):
|
||
r"""ResNet-50 model from
|
||
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_
|
||
|
||
Args:
|
||
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
||
progress (bool): If True, displays a progress bar of the download to stderr
|
||
"""
|
||
return _resnet(Bottleneck, [3, 4, 6, 3], **kwargs)
|
||
|
||
|
||
def resnet101(**kwargs):
|
||
r"""ResNet-101 model from
|
||
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_
|
||
|
||
Args:
|
||
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
||
progress (bool): If True, displays a progress bar of the download to stderr
|
||
"""
|
||
return _resnet(Bottleneck, [3, 4, 23, 3], **kwargs)
|
||
|
||
from typing import Dict, List
|
||
from collections import OrderedDict
|
||
from torch import nn, Tensor
|
||
class IntermediateLayerGetter(nn.ModuleDict):
|
||
"""
|
||
Module wrapper that returns intermediate layers from a model
|
||
|
||
It has a strong assumption that the modules have been registered
|
||
into the model in the same order as they are used.
|
||
This means that one should **not** reuse the same nn.Module
|
||
twice in the forward if you want this to work.
|
||
|
||
Additionally, it is only able to query submodules that are directly
|
||
assigned to the model. So if `model` is passed, `model.feature1` can
|
||
be returned, but not `model.feature1.layer2`.
|
||
|
||
Args:
|
||
model (nn.Module): model on which we will extract the features
|
||
return_layers (Dict[name, new_name]): a dict containing the names
|
||
of the modules for which the activations will be returned as
|
||
the key of the dict, and the value of the dict is the name
|
||
of the returned activation (which the user can specify).
|
||
"""
|
||
_version = 2
|
||
__annotations__ = {
|
||
"return_layers": Dict[str, str],
|
||
}
|
||
|
||
def __init__(self, model: nn.Module, return_layers: Dict[str, str]) -> None:
|
||
if not set(return_layers).issubset([name for name, _ in model.named_children()]):
|
||
raise ValueError("return_layers are not present in model")
|
||
orig_return_layers = return_layers
|
||
return_layers = {str(k): str(v) for k, v in return_layers.items()}
|
||
|
||
# 重新构建backbone，将没有使用到的模块全部删掉
|
||
layers = OrderedDict()
|
||
for name, module in model.named_children():
|
||
layers[name] = module
|
||
if name in return_layers:
|
||
del return_layers[name]
|
||
if not return_layers:
|
||
break
|
||
|
||
super(IntermediateLayerGetter, self).__init__(layers)
|
||
self.return_layers = orig_return_layers
|
||
|
||
def forward(self, x: Tensor) -> Dict[str, Tensor]:
|
||
out = OrderedDict()
|
||
for name, module in self.items():
|
||
x = module(x)
|
||
if name in self.return_layers:
|
||
out_name = self.return_layers[name]
|
||
out[out_name] = x
|
||
return out
|
||
|