File size: 9,794 Bytes
226675b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
import torch
import torch.nn as nn
import torch.nn.functional as F
#from torchvision import models
#from base import BaseModel
#from utils.helpers import initialize_weights
from itertools import chain
#from swin_transformer import SwinTransformer
from einops import rearrange
from torch.hub import load_state_dict_from_url
GlobalAvgPool2D = lambda: nn.AdaptiveAvgPool2d(1)
model_urls = {
'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
}
class Bottleneck(nn.Module):
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
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, strides=None):
super(ResNet, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
self._norm_layer = norm_layer
self.strides = strides
if self.strides is None:
self.strides = [2, 2, 2, 2, 2]
self.inplanes = 64
self.dilation = 1
if replace_stride_with_dilation is None:
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=self.strides[0], padding=3,
bias=False)
self.bn1 = norm_layer(self.inplanes)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=self.strides[1], padding=1)
self.maxpool1 = nn.MaxPool2d(kernel_size=3, stride=self.strides[1], padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=self.strides[2],
dilate=replace_stride_with_dilation[0])
self.layer3 = self._make_layer(block, 256, layers[2], stride=self.strides[3],
dilate=replace_stride_with_dilation[1])
self.layer4 = self._make_layer(block, 512, layers[3], stride=self.strides[4],
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.GroupNorm)):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
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)
self.channe1 = nn.Sequential(
nn.Conv2d(256, 64, kernel_size=1, padding=0, bias=False),
nn.BatchNorm2d(64),
nn.ReLU(inplace=True),
nn.Dropout2d(0.1)
)
self.channe2 = nn.Sequential(
nn.Conv2d(512, 128, kernel_size=1, padding=0, bias=False),
nn.BatchNorm2d(128),
nn.ReLU(inplace=True),
nn.Dropout2d(0.1)
)
self.channe3 = nn.Sequential(
nn.Conv2d(1024, 256, kernel_size=1, padding=0, bias=False),
nn.BatchNorm2d(256),
nn.ReLU(inplace=True),
nn.Dropout2d(0.1)
)
self.channe4 = nn.Sequential(
nn.Conv2d(2048, 512, kernel_size=1, padding=0, bias=False),
nn.BatchNorm2d(512),
nn.ReLU(inplace=True),
nn.Dropout2d(0.1)
)
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)
x0 = self.relu(x)
x00 = self.maxpool(x0)
x1 = self.layer1(x00)
x2 = self.layer2(x1)
x3 = self.layer3(x2)
x4 = self.layer4(x3)
x1 = self.channe1(x1)
x2 = self.channe2(x2)
x3 = self.channe3(x3)
x4 = self.channe4(x4)
return [x1, x2, x3, x4]
def forward(self, x):
return self._forward_impl(x)
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 BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
base_width=64, dilation=1, norm_layer=None):
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:
dilation = 1
# raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
# 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
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)
out += identity
out = self.relu(out)
return out
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
def resnet18(pretrained=False, progress=True, **kwargs):
return _resnet('resnet18', BasicBlock, [2, 2, 2, 2], pretrained, progress,
**kwargs)
def resnet50(pretrained=False, progress=True, **kwargs):
return _resnet('resnet50', Bottleneck, [3, 4, 6, 3], pretrained, progress,
**kwargs)
class SARASNet_backbone(nn.Module):
# Implementing only the object path
def __init__(self):
super(SARASNet_backbone, self).__init__()
# CNN-backbone
self.resnet = resnet50(pretrained=True, replace_stride_with_dilation=[False,True,True])
def forward(self, x1, x2):
# CNN-backbone
features1 = self.resnet(x1)
features2 = self.resnet(x2)
return [features1, features2]
if __name__ == '__main__':
xa = torch.randn(4, 3, 256, 256)
xb = torch.randn(4, 3, 256, 256)
net = SARASNet_backbone()
out = net(xa, xb)
print(out.shape) |