481 lines
19 KiB
Python
481 lines
19 KiB
Python
import torch
|
|
import torch.nn as nn
|
|
from config import config as conf
|
|
|
|
try:
|
|
from torch.hub import load_state_dict_from_url
|
|
except ImportError:
|
|
from torch.utils.model_zoo import load_url as load_state_dict_from_url
|
|
# from .utils import load_state_dict_from_url
|
|
|
|
__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
|
|
'resnet152', 'resnext50_32x4d', 'resnext101_32x8d',
|
|
'wide_resnet50_2', 'wide_resnet101_2']
|
|
|
|
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',
|
|
'resnext50_32x4d': 'https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth',
|
|
'resnext101_32x8d': 'https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth',
|
|
'wide_resnet50_2': 'https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth',
|
|
'wide_resnet101_2': 'https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth',
|
|
}
|
|
|
|
|
|
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 SpatialAttention(nn.Module):
|
|
def __init__(self, kernel_size=7):
|
|
super(SpatialAttention, self).__init__()
|
|
|
|
assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
|
|
padding = 3 if kernel_size == 7 else 1
|
|
|
|
self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
|
|
self.sigmoid = nn.Sigmoid()
|
|
|
|
def forward(self, x):
|
|
avg_out = torch.mean(x, dim=1, keepdim=True)
|
|
max_out, _ = torch.max(x, dim=1, keepdim=True)
|
|
x = torch.cat([avg_out, max_out], dim=1)
|
|
x = self.conv1(x)
|
|
return self.sigmoid(x)
|
|
|
|
|
|
class BasicBlock(nn.Module):
|
|
expansion = 1
|
|
|
|
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
|
|
base_width=64, dilation=1, norm_layer=None, cam=False, bam=False):
|
|
super(BasicBlock, self).__init__()
|
|
if norm_layer is None:
|
|
norm_layer = nn.BatchNorm2d
|
|
if groups != 1 or base_width != 64:
|
|
raise ValueError('BasicBlock only supports groups=1 and base_width=64')
|
|
if dilation > 1:
|
|
raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
|
|
self.cam = cam
|
|
self.bam = bam
|
|
# Both self.conv1 and self.downsample layers downsample the input when stride != 1
|
|
self.conv1 = conv3x3(inplanes, planes, stride)
|
|
self.bn1 = norm_layer(planes)
|
|
self.relu = nn.ReLU(inplace=True)
|
|
self.conv2 = conv3x3(planes, planes)
|
|
self.bn2 = norm_layer(planes)
|
|
self.downsample = downsample
|
|
self.stride = stride
|
|
if self.cam:
|
|
if planes == 64:
|
|
self.globalAvgPool = nn.AvgPool2d(56, stride=1)
|
|
elif planes == 128:
|
|
self.globalAvgPool = nn.AvgPool2d(28, stride=1)
|
|
elif planes == 256:
|
|
self.globalAvgPool = nn.AvgPool2d(14, stride=1)
|
|
elif planes == 512:
|
|
self.globalAvgPool = nn.AvgPool2d(7, stride=1)
|
|
|
|
self.fc1 = nn.Linear(in_features=planes, out_features=round(planes / 16))
|
|
self.fc2 = nn.Linear(in_features=round(planes / 16), out_features=planes)
|
|
self.sigmod = nn.Sigmoid()
|
|
if self.bam:
|
|
self.bam = SpatialAttention()
|
|
|
|
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)
|
|
|
|
if self.downsample is not None:
|
|
identity = self.downsample(x)
|
|
|
|
if self.cam:
|
|
ori_out = self.globalAvgPool(out)
|
|
out = out.view(out.size(0), -1)
|
|
out = self.fc1(out)
|
|
out = self.relu(out)
|
|
out = self.fc2(out)
|
|
out = self.sigmod(out)
|
|
out = out.view(out.size(0), out.size(-1), 1, 1)
|
|
out = out * ori_out
|
|
|
|
if self.bam:
|
|
out = out * self.bam(out)
|
|
|
|
out += identity
|
|
out = self.relu(out)
|
|
|
|
return out
|
|
|
|
|
|
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, cam=False, bam=False):
|
|
super(Bottleneck, self).__init__()
|
|
if norm_layer is None:
|
|
norm_layer = nn.BatchNorm2d
|
|
width = int(planes * (base_width / 64.)) * groups
|
|
self.cam = cam
|
|
self.bam = bam
|
|
# 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
|
|
if self.cam:
|
|
if planes == 64:
|
|
self.globalAvgPool = nn.AvgPool2d(56, stride=1)
|
|
elif planes == 128:
|
|
self.globalAvgPool = nn.AvgPool2d(28, stride=1)
|
|
elif planes == 256:
|
|
self.globalAvgPool = nn.AvgPool2d(14, stride=1)
|
|
elif planes == 512:
|
|
self.globalAvgPool = nn.AvgPool2d(7, stride=1)
|
|
|
|
self.fc1 = nn.Linear(planes * self.expansion, round(planes / 4))
|
|
self.fc2 = nn.Linear(round(planes / 4), planes * self.expansion)
|
|
self.sigmod = nn.Sigmoid()
|
|
|
|
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)
|
|
|
|
if self.cam:
|
|
ori_out = self.globalAvgPool(out)
|
|
out = out.view(out.size(0), -1)
|
|
out = self.fc1(out)
|
|
out = self.relu(out)
|
|
out = self.fc2(out)
|
|
out = self.sigmod(out)
|
|
out = out.view(out.size(0), out.size(-1), 1, 1)
|
|
out = out * ori_out
|
|
out += identity
|
|
out = self.relu(out)
|
|
return out
|
|
|
|
|
|
class ResNet(nn.Module):
|
|
|
|
def __init__(self, block, layers, num_classes=conf.embedding_size, zero_init_residual=False,
|
|
groups=1, width_per_group=64, replace_stride_with_dilation=None,
|
|
norm_layer=None, scale=conf.channel_ratio):
|
|
super(ResNet, self).__init__()
|
|
if norm_layer is None:
|
|
norm_layer = nn.BatchNorm2d
|
|
self._norm_layer = norm_layer
|
|
print("通道剪枝 {}".format(scale))
|
|
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.adaptiveMaxPool = nn.AdaptiveMaxPool2d((1, 1))
|
|
# self.maxpool2 = nn.Sequential(
|
|
# nn.MaxPool2d(kernel_size=2, stride=2, padding=0),
|
|
# nn.MaxPool2d(kernel_size=2, stride=2, padding=0),
|
|
# nn.MaxPool2d(kernel_size=2, stride=2, padding=0),
|
|
# nn.MaxPool2d(kernel_size=2, stride=1, padding=0)
|
|
# )
|
|
self.layer1 = self._make_layer(block, int(64 * scale), layers[0])
|
|
self.layer2 = self._make_layer(block, int(128 * scale), layers[1], stride=2,
|
|
dilate=replace_stride_with_dilation[0])
|
|
self.layer3 = self._make_layer(block, int(256 * scale), layers[2], stride=2,
|
|
dilate=replace_stride_with_dilation[1])
|
|
self.layer4 = self._make_layer(block, int(512 * scale), layers[3], stride=2,
|
|
dilate=replace_stride_with_dilation[2])
|
|
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
|
|
self.fc = nn.Linear(int(512 * block.expansion * scale), 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.GroupNorm)):
|
|
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)
|
|
elif isinstance(m, BasicBlock):
|
|
nn.init.constant_(m.bn2.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):
|
|
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 = torch.flatten(x, 1)
|
|
x = self.fc(x)
|
|
|
|
return x
|
|
|
|
def forward(self, x):
|
|
return self._forward_impl(x)
|
|
|
|
|
|
# def _resnet(arch, block, layers, pretrained, progress, **kwargs):
|
|
# model = ResNet(block, layers, **kwargs)
|
|
# if pretrained:
|
|
# state_dict = load_state_dict_from_url(model_urls[arch],
|
|
# progress=progress)
|
|
# model.load_state_dict(state_dict, strict=False)
|
|
# return model
|
|
|
|
class CustomResNet18(nn.Module):
|
|
def __init__(self, model, num_classes=conf.custom_num_classes):
|
|
super(CustomResNet18, self).__init__()
|
|
self.custom_model = nn.Sequential(*list(model.children())[:-1])
|
|
self.fc = nn.Linear(model.fc.in_features, num_classes)
|
|
|
|
def forward(self, x):
|
|
x = self.custom_model(x)
|
|
x = x.view(x.size(0), -1)
|
|
x = self.fc(x)
|
|
return x
|
|
def _resnet(arch, block, layers, pretrained, progress, **kwargs):
|
|
model = ResNet(block, layers, **kwargs)
|
|
if pretrained:
|
|
state_dict = load_state_dict_from_url(model_urls[arch],
|
|
progress=progress)
|
|
|
|
src_state_dict = state_dict
|
|
target_state_dict = model.state_dict()
|
|
skip_keys = []
|
|
# skip mismatch size tensors in case of pretraining
|
|
for k in src_state_dict.keys():
|
|
if k not in target_state_dict:
|
|
continue
|
|
if src_state_dict[k].size() != target_state_dict[k].size():
|
|
skip_keys.append(k)
|
|
for k in skip_keys:
|
|
del src_state_dict[k]
|
|
missing_keys, unexpected_keys = model.load_state_dict(src_state_dict, strict=False)
|
|
|
|
return model
|
|
|
|
|
|
def resnet14(pretrained=True, progress=True, **kwargs):
|
|
r"""ResNet-14 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('resnet18', BasicBlock, [2, 1, 1, 2], pretrained, progress,
|
|
**kwargs)
|
|
|
|
|
|
def resnet18(pretrained=True, progress=True, **kwargs):
|
|
r"""ResNet-18 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
|
|
**kwargs: Additional arguments passed to ResNet, including:
|
|
scale (float): Channel scaling ratio (default: conf.channel_ratio)
|
|
"""
|
|
return _resnet('resnet18', BasicBlock, [2, 2, 2, 2], pretrained, progress,
|
|
**kwargs)
|
|
|
|
|
|
def resnet34(pretrained=True, progress=True, **kwargs):
|
|
r"""ResNet-34 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('resnet34', BasicBlock, [3, 4, 6, 3], pretrained, progress,
|
|
**kwargs)
|
|
|
|
|
|
def resnet50(pretrained=True, progress=True, **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('resnet50', Bottleneck, [3, 4, 6, 3], pretrained, progress,
|
|
**kwargs)
|
|
|
|
|
|
def resnet101(pretrained=True, progress=True, **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('resnet101', Bottleneck, [3, 4, 23, 3], pretrained, progress,
|
|
**kwargs)
|
|
|
|
|
|
def resnet152(pretrained=False, progress=True, **kwargs):
|
|
r"""ResNet-152 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('resnet152', Bottleneck, [3, 8, 36, 3], pretrained, progress,
|
|
**kwargs)
|
|
|
|
|
|
def resnext50_32x4d(pretrained=False, progress=True, **kwargs):
|
|
r"""ResNeXt-50 32x4d model from
|
|
`"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.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
|
|
"""
|
|
kwargs['groups'] = 32
|
|
kwargs['width_per_group'] = 4
|
|
return _resnet('resnext50_32x4d', Bottleneck, [3, 4, 6, 3],
|
|
pretrained, progress, **kwargs)
|
|
|
|
|
|
def resnext101_32x8d(pretrained=False, progress=True, **kwargs):
|
|
r"""ResNeXt-101 32x8d model from
|
|
`"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.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
|
|
"""
|
|
kwargs['groups'] = 32
|
|
kwargs['width_per_group'] = 8
|
|
return _resnet('resnext101_32x8d', Bottleneck, [3, 4, 23, 3],
|
|
pretrained, progress, **kwargs)
|
|
|
|
|
|
def wide_resnet50_2(pretrained=False, progress=True, **kwargs):
|
|
r"""Wide ResNet-50-2 model from
|
|
`"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_
|
|
|
|
The model is the same as ResNet except for the bottleneck number of channels
|
|
which is twice larger in every block. The number of channels in outer 1x1
|
|
convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
|
|
channels, and in Wide ResNet-50-2 has 2048-1024-2048.
|
|
|
|
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
|
|
"""
|
|
kwargs['width_per_group'] = 64 * 2
|
|
return _resnet('wide_resnet50_2', Bottleneck, [3, 4, 6, 3],
|
|
pretrained, progress, **kwargs)
|
|
|
|
|
|
def wide_resnet101_2(pretrained=False, progress=True, **kwargs):
|
|
r"""Wide ResNet-101-2 model from
|
|
`"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_
|
|
|
|
The model is the same as ResNet except for the bottleneck number of channels
|
|
which is twice larger in every block. The number of channels in outer 1x1
|
|
convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
|
|
channels, and in Wide ResNet-50-2 has 2048-1024-2048.
|
|
|
|
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
|
|
"""
|
|
kwargs['width_per_group'] = 64 * 2
|
|
return _resnet('wide_resnet101_2', Bottleneck, [3, 4, 23, 3],
|
|
pretrained, progress, **kwargs)
|