Spaces:
Running
on
Zero
Running
on
Zero
File size: 10,220 Bytes
ff715ca |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 |
import torch.nn as nn
import math
# import torch.utils.model_zoo as model_zoo
import torch
import numpy as np
import torch.nn.functional as F
affine_par = True
# def outS(i):
# i = int(i)
# i = (i+1)/2
# i = int(np.ceil((i+1)/2.0))
# i = (i+1)/2
# return i
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, affine = affine_par)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes, affine = affine_par)
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, dilation_ = 1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, stride=stride, bias=False) # change
self.bn1 = nn.BatchNorm2d(planes,affine = affine_par)
for i in self.bn1.parameters():
i.requires_grad = False
padding = 1
if dilation_ == 2:
padding = 2
elif dilation_ == 4:
padding = 4
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, # change
padding=padding, bias=False, dilation = dilation_)
self.bn2 = nn.BatchNorm2d(planes,affine = affine_par)
for i in self.bn2.parameters():
i.requires_grad = False
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4, affine = affine_par)
for i in self.bn3.parameters():
i.requires_grad = False
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
class ResNet(nn.Module):
def __init__(self, block, layers):
self.inplanes = 64
super(ResNet, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64,affine = affine_par)
for i in self.bn1.parameters():
i.requires_grad = False
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1, ceil_mode=True) # change
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=1, dilation__ = 2)
# self.layer4 = self._make_layer(block, 512, layers[3], stride=1, dilation__ = 4)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=1, dilation__ = 2)
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, 0.01)
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
# for i in m.parameters():
# i.requires_grad = False
def _make_layer(self, block, planes, blocks, stride=1,dilation__ = 1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion or dilation__ == 2 or dilation__ == 4:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion,affine = affine_par),
)
for i in downsample._modules['1'].parameters():
i.requires_grad = False
layers = []
layers.append(block(self.inplanes, planes, stride,dilation_=dilation__, downsample = downsample ))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes,dilation_=dilation__))
return nn.Sequential(*layers)
# def _make_pred_layer(self,block, dilation_series, padding_series,NoLabels):
# return block(dilation_series,padding_series,NoLabels)
def forward(self, x):
tmp_x = []
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
tmp_x.append(x)
x = self.maxpool(x)
x = self.layer1(x)
tmp_x.append(x)
x = self.layer2(x)
tmp_x.append(x)
x = self.layer3(x)
tmp_x.append(x)
x = self.layer4(x)
tmp_x.append(x)
return tmp_x
class ResNet_locate(nn.Module):
def __init__(self, block, layers):
super(ResNet_locate,self).__init__()
self.resnet = ResNet(block, layers)
self.in_planes = 512
self.out_planes = [512, 256, 256, 128]
self.ppms_pre = nn.Conv2d(2048, self.in_planes, 1, 1, bias=False)
ppms, infos = [], []
for ii in [1, 3, 5]:
ppms.append(nn.Sequential(nn.AdaptiveAvgPool2d(ii), nn.Conv2d(self.in_planes, self.in_planes, 1, 1, bias=False), nn.ReLU(inplace=True)))
self.ppms = nn.ModuleList(ppms)
self.ppm_cat = nn.Sequential(nn.Conv2d(self.in_planes * 4, self.in_planes, 3, 1, 1, bias=False), nn.ReLU(inplace=True))
# self.ppm_score = nn.Conv2d(self.in_planes, 1, 1, 1)
for ii in self.out_planes:
infos.append(nn.Sequential(nn.Conv2d(self.in_planes, ii, 3, 1, 1, bias=False), nn.ReLU(inplace=True)))
self.infos = nn.ModuleList(infos)
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, 0.01)
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def load_pretrained_model(self, model):
self.resnet.load_state_dict(model)
def forward(self, x):
x_size = x.size()[2:]
xs = self.resnet(x)
xs_1 = self.ppms_pre(xs[-1])
xls = [xs_1]
for k in range(len(self.ppms)):
xls.append(F.interpolate(self.ppms[k](xs_1), xs_1.size()[2:], mode='bilinear', align_corners=True))
xls = self.ppm_cat(torch.cat(xls, dim=1))
top_score = None
# top_score = F.interpolate(self.ppm_score(xls), x_size, mode='bilinear', align_corners=True)
infos = []
for k in range(len(self.infos)):
infos.append(self.infos[k](F.interpolate(xls, xs[len(self.infos) - 1 - k].size()[2:], mode='bilinear', align_corners=True)))
return xs, top_score, infos
class BottleneckEZ(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, dilation_ = 1, downsample=None):
super(BottleneckEZ, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, stride=stride, bias=False) # change
# self.bn1 = nn.BatchNorm2d(planes,affine = affine_par)
# for i in self.bn1.parameters():
# i.requires_grad = False
padding = 1
if dilation_ == 2:
padding = 2
elif dilation_ == 4:
padding = 4
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, # change
padding=padding, bias=False, dilation = dilation_)
# self.bn2 = nn.BatchNorm2d(planes,affine = affine_par)
# for i in self.bn2.parameters():
# i.requires_grad = False
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
# self.bn3 = nn.BatchNorm2d(planes * 4, affine = affine_par)
# for i in self.bn3.parameters():
# i.requires_grad = False
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
def resnet50(pretrained=False):
"""Constructs a ResNet-50 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
# model = ResNet(Bottleneck, [3, 4, 6, 3])
model = ResNet(Bottleneck, [3, 4, 6, 3])
if pretrained:
model.load_state_dict(load_url(model_urls['resnet50']), strict=False)
return model
def resnet101(pretrained=False):
"""Constructs a ResNet-101 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
# model = ResNet(Bottleneck, [3, 4, 23, 3])
model = ResNet_locate(Bottleneck, [3, 4, 23, 3])
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
return model
|