taesiri's picture
Initial Commit
8390f90
raw
history blame
4.9 kB
r""" ResNet-101 backbone network """
import torch.utils.model_zoo as model_zoo
import torch.nn as nn
import torch
__all__ = ['Backbone', 'resnet101']
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):
r""" 3x3 convolution with padding """
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=1, groups=2, bias=False)
def conv1x1(in_planes, out_planes, stride=1):
r""" 1x1 convolution """
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, groups=2, bias=False)
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = conv1x1(inplanes, planes)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = conv3x3(planes, planes, stride)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = conv1x1(planes, planes * self.expansion)
self.bn3 = nn.BatchNorm2d(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 Backbone(nn.Module):
def __init__(self, block, layers, zero_init_residual=False):
super(Backbone, self).__init__()
self.inplanes = 128
self.conv1 = nn.Conv2d(6, 128, kernel_size=7, stride=2, padding=3, groups=2,
bias=False)
self.bn1 = nn.BatchNorm2d(128)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 128, layers[0])
self.layer2 = self._make_layer(block, 256, layers[1], stride=2)
self.layer3 = self._make_layer(block, 512, layers[2], stride=2)
self.layer4 = self._make_layer(block, 1024, layers[3], stride=2)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(512 * block.expansion, 1000)
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):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
conv1x1(self.inplanes, planes * block.expansion, stride),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for _ in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def resnet101(pretrained=False, **kwargs):
"""Constructs a ResNet-101 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = Backbone(Bottleneck, [3, 4, 23, 3], **kwargs)
if pretrained:
weights = model_zoo.load_url(model_urls['resnet101'])
for key in weights:
if key.split('.')[0] == 'fc':
weights[key] = weights[key].clone()
continue
weights[key] = torch.cat([weights[key].clone(), weights[key].clone()], dim=0)
model.load_state_dict(weights)
return model