File size: 8,276 Bytes
0870534 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 |
import torch
import torch.nn as nn
from .lseg_vit import (
_make_pretrained_clip_vitl16_384,
_make_pretrained_clip_vitb32_384,
_make_pretrained_clipRN50x16_vitl16_384,
forward_vit,
)
def _make_encoder(
backbone,
features,
use_pretrained=True,
groups=1,
expand=False,
exportable=True,
hooks=None,
use_vit_only=False,
use_readout="ignore",
enable_attention_hooks=False,
):
if backbone == "clip_vitl16_384":
clip_pretrained, pretrained = _make_pretrained_clip_vitl16_384(
use_pretrained,
hooks=hooks,
use_readout=use_readout,
enable_attention_hooks=enable_attention_hooks,
)
scratch = _make_scratch(
[256, 512, 1024, 1024], features, groups=groups, expand=expand
)
elif backbone == "clipRN50x16_vitl16_384":
clip_pretrained, pretrained = _make_pretrained_clipRN50x16_vitl16_384(
use_pretrained,
hooks=hooks,
use_readout=use_readout,
enable_attention_hooks=enable_attention_hooks,
)
scratch = _make_scratch(
[256, 512, 1024, 1024], features, groups=groups, expand=expand
)
elif backbone == "clip_vitb32_384":
clip_pretrained, pretrained = _make_pretrained_clip_vitb32_384(
use_pretrained,
hooks=hooks,
use_readout=use_readout,
)
scratch = _make_scratch(
[96, 192, 384, 768], features, groups=groups, expand=expand
)
else:
print(f"Backbone '{backbone}' not implemented")
assert False
return clip_pretrained, pretrained, scratch
def _make_scratch(in_shape, out_shape, groups=1, expand=False):
scratch = nn.Module()
out_shape1 = out_shape
out_shape2 = out_shape
out_shape3 = out_shape
out_shape4 = out_shape
if expand == True:
out_shape1 = out_shape
out_shape2 = out_shape * 2
out_shape3 = out_shape * 4
out_shape4 = out_shape * 8
scratch.layer1_rn = nn.Conv2d(
in_shape[0],
out_shape1,
kernel_size=3,
stride=1,
padding=1,
bias=False,
groups=groups,
)
scratch.layer2_rn = nn.Conv2d(
in_shape[1],
out_shape2,
kernel_size=3,
stride=1,
padding=1,
bias=False,
groups=groups,
)
scratch.layer3_rn = nn.Conv2d(
in_shape[2],
out_shape3,
kernel_size=3,
stride=1,
padding=1,
bias=False,
groups=groups,
)
scratch.layer4_rn = nn.Conv2d(
in_shape[3],
out_shape4,
kernel_size=3,
stride=1,
padding=1,
bias=False,
groups=groups,
)
return scratch
class Interpolate(nn.Module):
"""Interpolation module."""
def __init__(self, scale_factor, mode, align_corners=False):
"""Init.
Args:
scale_factor (float): scaling
mode (str): interpolation mode
"""
super(Interpolate, self).__init__()
self.interp = nn.functional.interpolate
self.scale_factor = scale_factor
self.mode = mode
self.align_corners = align_corners
def forward(self, x):
"""Forward pass.
Args:
x (tensor): input
Returns:
tensor: interpolated data
"""
x = self.interp(
x,
scale_factor=self.scale_factor,
mode=self.mode,
align_corners=self.align_corners,
)
return x
class ResidualConvUnit(nn.Module):
"""Residual convolution module."""
def __init__(self, features):
"""Init.
Args:
features (int): number of features
"""
super().__init__()
self.conv1 = nn.Conv2d(
features, features, kernel_size=3, stride=1, padding=1, bias=True
)
self.conv2 = nn.Conv2d(
features, features, kernel_size=3, stride=1, padding=1, bias=True
)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
"""Forward pass.
Args:
x (tensor): input
Returns:
tensor: output
"""
out = self.relu(x)
out = self.conv1(out)
out = self.relu(out)
out = self.conv2(out)
return out + x
class FeatureFusionBlock(nn.Module):
"""Feature fusion block."""
def __init__(self, features):
"""Init.
Args:
features (int): number of features
"""
super(FeatureFusionBlock, self).__init__()
self.resConfUnit1 = ResidualConvUnit(features)
self.resConfUnit2 = ResidualConvUnit(features)
def forward(self, *xs):
"""Forward pass.
Returns:
tensor: output
"""
output = xs[0]
if len(xs) == 2:
output += self.resConfUnit1(xs[1])
output = self.resConfUnit2(output)
output = nn.functional.interpolate(
output, scale_factor=2, mode="bilinear", align_corners=True
)
return output
class ResidualConvUnit_custom(nn.Module):
"""Residual convolution module."""
def __init__(self, features, activation, bn):
"""Init.
Args:
features (int): number of features
"""
super().__init__()
self.bn = bn
self.groups = 1
self.conv1 = nn.Conv2d(
features,
features,
kernel_size=3,
stride=1,
padding=1,
bias=not self.bn,
groups=self.groups,
)
self.conv2 = nn.Conv2d(
features,
features,
kernel_size=3,
stride=1,
padding=1,
bias=not self.bn,
groups=self.groups,
)
if self.bn == True:
self.bn1 = nn.BatchNorm2d(features)
self.bn2 = nn.BatchNorm2d(features)
self.activation = activation
self.skip_add = nn.quantized.FloatFunctional()
def forward(self, x):
"""Forward pass.
Args:
x (tensor): input
Returns:
tensor: output
"""
out = self.activation(x)
out = self.conv1(out)
if self.bn == True:
out = self.bn1(out)
out = self.activation(out)
out = self.conv2(out)
if self.bn == True:
out = self.bn2(out)
if self.groups > 1:
out = self.conv_merge(out)
return self.skip_add.add(out, x)
# return out + x
class FeatureFusionBlock_custom(nn.Module):
"""Feature fusion block."""
def __init__(
self,
features,
activation,
deconv=False,
bn=False,
expand=False,
align_corners=True,
):
"""Init.
Args:
features (int): number of features
"""
super(FeatureFusionBlock_custom, self).__init__()
self.deconv = deconv
self.align_corners = align_corners
self.groups = 1
self.expand = expand
out_features = features
if self.expand == True:
out_features = features // 2
self.out_conv = nn.Conv2d(
features,
out_features,
kernel_size=1,
stride=1,
padding=0,
bias=True,
groups=1,
)
self.resConfUnit1 = ResidualConvUnit_custom(features, activation, bn)
self.resConfUnit2 = ResidualConvUnit_custom(features, activation, bn)
self.skip_add = nn.quantized.FloatFunctional()
def forward(self, *xs):
"""Forward pass.
Returns:
tensor: output
"""
output = xs[0]
if len(xs) == 2:
res = self.resConfUnit1(xs[1])
output = self.skip_add.add(output, res)
# output += res
output = self.resConfUnit2(output)
output = nn.functional.interpolate(
output, scale_factor=2, mode="bilinear", align_corners=self.align_corners
)
output = self.out_conv(output)
return output
|