from __future__ import division, absolute_import
import torch
import torch.utils.model_zoo as model_zoo
from torch import nn
__all__ = ['resnet50mid']
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 * self.expansion, kernel_size=1, bias=False
)
self.bn3 = nn.BatchNorm2d(planes * self.expansion)
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
[docs]class ResNetMid(nn.Module):
"""Residual network + mid-level features.
Reference:
Yu et al. The Devil is in the Middle: Exploiting Mid-level Representations for
Cross-Domain Instance Matching. arXiv:1711.08106.
Public keys:
- ``resnet50mid``: ResNet50 + mid-level feature fusion.
"""
def __init__(
self,
num_classes,
loss,
block,
layers,
last_stride=2,
fc_dims=None,
**kwargs
):
self.inplanes = 64
super(ResNetMid, self).__init__()
self.loss = loss
self.feature_dim = 512 * block.expansion
# backbone network
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=last_stride
)
self.global_avgpool = nn.AdaptiveAvgPool2d(1)
assert fc_dims is not None
self.fc_fusion = self._construct_fc_layer(
fc_dims, 512 * block.expansion * 2
)
self.feature_dim += 512 * block.expansion
self.classifier = nn.Linear(self.feature_dim, num_classes)
self._init_params()
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 _construct_fc_layer(self, fc_dims, input_dim, dropout_p=None):
"""Constructs fully connected layer
Args:
fc_dims (list or tuple): dimensions of fc layers, if None, no fc layers are constructed
input_dim (int): input dimension
dropout_p (float): dropout probability, if None, dropout is unused
"""
if fc_dims is None:
self.feature_dim = input_dim
return None
assert isinstance(
fc_dims, (list, tuple)
), 'fc_dims must be either list or tuple, but got {}'.format(
type(fc_dims)
)
layers = []
for dim in fc_dims:
layers.append(nn.Linear(input_dim, dim))
layers.append(nn.BatchNorm1d(dim))
layers.append(nn.ReLU(inplace=True))
if dropout_p is not None:
layers.append(nn.Dropout(p=dropout_p))
input_dim = dim
self.feature_dim = fc_dims[-1]
return nn.Sequential(*layers)
def _init_params(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(
m.weight, mode='fan_out', nonlinearity='relu'
)
if m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.BatchNorm1d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
if m.bias is not None:
nn.init.constant_(m.bias, 0)
def featuremaps(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)
x4a = self.layer4[0](x)
x4b = self.layer4[1](x4a)
x4c = self.layer4[2](x4b)
return x4a, x4b, x4c
def forward(self, x):
x4a, x4b, x4c = self.featuremaps(x)
v4a = self.global_avgpool(x4a)
v4b = self.global_avgpool(x4b)
v4c = self.global_avgpool(x4c)
v4ab = torch.cat([v4a, v4b], 1)
v4ab = v4ab.view(v4ab.size(0), -1)
v4ab = self.fc_fusion(v4ab)
v4c = v4c.view(v4c.size(0), -1)
v = torch.cat([v4ab, v4c], 1)
if not self.training:
return v
y = self.classifier(v)
if self.loss == 'softmax':
return y
elif self.loss == 'triplet':
return y, v
else:
raise KeyError('Unsupported loss: {}'.format(self.loss))
def init_pretrained_weights(model, model_url):
"""Initializes model with pretrained weights.
Layers that don't match with pretrained layers in name or size are kept unchanged.
"""
pretrain_dict = model_zoo.load_url(model_url)
model_dict = model.state_dict()
pretrain_dict = {
k: v
for k, v in pretrain_dict.items()
if k in model_dict and model_dict[k].size() == v.size()
}
model_dict.update(pretrain_dict)
model.load_state_dict(model_dict)
"""
Residual network configurations:
--
resnet18: block=BasicBlock, layers=[2, 2, 2, 2]
resnet34: block=BasicBlock, layers=[3, 4, 6, 3]
resnet50: block=Bottleneck, layers=[3, 4, 6, 3]
resnet101: block=Bottleneck, layers=[3, 4, 23, 3]
resnet152: block=Bottleneck, layers=[3, 8, 36, 3]
"""
def resnet50mid(num_classes, loss='softmax', pretrained=True, **kwargs):
model = ResNetMid(
num_classes=num_classes,
loss=loss,
block=Bottleneck,
layers=[3, 4, 6, 3],
last_stride=2,
fc_dims=[1024],
**kwargs
)
if pretrained:
init_pretrained_weights(model, model_urls['resnet50'])
return model