Spaces:
Paused
Paused
File size: 24,290 Bytes
3f9c56c |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 |
import torch.nn as nn
import torch.utils.checkpoint as cp
from annotator.mmpkg.mmcv.cnn import (build_conv_layer, build_norm_layer, build_plugin_layer,
constant_init, kaiming_init)
from annotator.mmpkg.mmcv.runner import load_checkpoint
from annotator.mmpkg.mmcv.utils.parrots_wrapper import _BatchNorm
from annotator.mmpkg.mmseg.utils import get_root_logger
from ..builder import BACKBONES
from ..utils import ResLayer
class BasicBlock(nn.Module):
"""Basic block for ResNet."""
expansion = 1
def __init__(self,
inplanes,
planes,
stride=1,
dilation=1,
downsample=None,
style='pytorch',
with_cp=False,
conv_cfg=None,
norm_cfg=dict(type='BN'),
dcn=None,
plugins=None):
super(BasicBlock, self).__init__()
assert dcn is None, 'Not implemented yet.'
assert plugins is None, 'Not implemented yet.'
self.norm1_name, norm1 = build_norm_layer(norm_cfg, planes, postfix=1)
self.norm2_name, norm2 = build_norm_layer(norm_cfg, planes, postfix=2)
self.conv1 = build_conv_layer(
conv_cfg,
inplanes,
planes,
3,
stride=stride,
padding=dilation,
dilation=dilation,
bias=False)
self.add_module(self.norm1_name, norm1)
self.conv2 = build_conv_layer(
conv_cfg, planes, planes, 3, padding=1, bias=False)
self.add_module(self.norm2_name, norm2)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
self.dilation = dilation
self.with_cp = with_cp
@property
def norm1(self):
"""nn.Module: normalization layer after the first convolution layer"""
return getattr(self, self.norm1_name)
@property
def norm2(self):
"""nn.Module: normalization layer after the second convolution layer"""
return getattr(self, self.norm2_name)
def forward(self, x):
"""Forward function."""
def _inner_forward(x):
identity = x
out = self.conv1(x)
out = self.norm1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.norm2(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
return out
if self.with_cp and x.requires_grad:
out = cp.checkpoint(_inner_forward, x)
else:
out = _inner_forward(x)
out = self.relu(out)
return out
class Bottleneck(nn.Module):
"""Bottleneck block for ResNet.
If style is "pytorch", the stride-two layer is the 3x3 conv layer, if it is
"caffe", the stride-two layer is the first 1x1 conv layer.
"""
expansion = 4
def __init__(self,
inplanes,
planes,
stride=1,
dilation=1,
downsample=None,
style='pytorch',
with_cp=False,
conv_cfg=None,
norm_cfg=dict(type='BN'),
dcn=None,
plugins=None):
super(Bottleneck, self).__init__()
assert style in ['pytorch', 'caffe']
assert dcn is None or isinstance(dcn, dict)
assert plugins is None or isinstance(plugins, list)
if plugins is not None:
allowed_position = ['after_conv1', 'after_conv2', 'after_conv3']
assert all(p['position'] in allowed_position for p in plugins)
self.inplanes = inplanes
self.planes = planes
self.stride = stride
self.dilation = dilation
self.style = style
self.with_cp = with_cp
self.conv_cfg = conv_cfg
self.norm_cfg = norm_cfg
self.dcn = dcn
self.with_dcn = dcn is not None
self.plugins = plugins
self.with_plugins = plugins is not None
if self.with_plugins:
# collect plugins for conv1/conv2/conv3
self.after_conv1_plugins = [
plugin['cfg'] for plugin in plugins
if plugin['position'] == 'after_conv1'
]
self.after_conv2_plugins = [
plugin['cfg'] for plugin in plugins
if plugin['position'] == 'after_conv2'
]
self.after_conv3_plugins = [
plugin['cfg'] for plugin in plugins
if plugin['position'] == 'after_conv3'
]
if self.style == 'pytorch':
self.conv1_stride = 1
self.conv2_stride = stride
else:
self.conv1_stride = stride
self.conv2_stride = 1
self.norm1_name, norm1 = build_norm_layer(norm_cfg, planes, postfix=1)
self.norm2_name, norm2 = build_norm_layer(norm_cfg, planes, postfix=2)
self.norm3_name, norm3 = build_norm_layer(
norm_cfg, planes * self.expansion, postfix=3)
self.conv1 = build_conv_layer(
conv_cfg,
inplanes,
planes,
kernel_size=1,
stride=self.conv1_stride,
bias=False)
self.add_module(self.norm1_name, norm1)
fallback_on_stride = False
if self.with_dcn:
fallback_on_stride = dcn.pop('fallback_on_stride', False)
if not self.with_dcn or fallback_on_stride:
self.conv2 = build_conv_layer(
conv_cfg,
planes,
planes,
kernel_size=3,
stride=self.conv2_stride,
padding=dilation,
dilation=dilation,
bias=False)
else:
assert self.conv_cfg is None, 'conv_cfg must be None for DCN'
self.conv2 = build_conv_layer(
dcn,
planes,
planes,
kernel_size=3,
stride=self.conv2_stride,
padding=dilation,
dilation=dilation,
bias=False)
self.add_module(self.norm2_name, norm2)
self.conv3 = build_conv_layer(
conv_cfg,
planes,
planes * self.expansion,
kernel_size=1,
bias=False)
self.add_module(self.norm3_name, norm3)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
if self.with_plugins:
self.after_conv1_plugin_names = self.make_block_plugins(
planes, self.after_conv1_plugins)
self.after_conv2_plugin_names = self.make_block_plugins(
planes, self.after_conv2_plugins)
self.after_conv3_plugin_names = self.make_block_plugins(
planes * self.expansion, self.after_conv3_plugins)
def make_block_plugins(self, in_channels, plugins):
"""make plugins for block.
Args:
in_channels (int): Input channels of plugin.
plugins (list[dict]): List of plugins cfg to build.
Returns:
list[str]: List of the names of plugin.
"""
assert isinstance(plugins, list)
plugin_names = []
for plugin in plugins:
plugin = plugin.copy()
name, layer = build_plugin_layer(
plugin,
in_channels=in_channels,
postfix=plugin.pop('postfix', ''))
assert not hasattr(self, name), f'duplicate plugin {name}'
self.add_module(name, layer)
plugin_names.append(name)
return plugin_names
def forward_plugin(self, x, plugin_names):
"""Forward function for plugins."""
out = x
for name in plugin_names:
out = getattr(self, name)(x)
return out
@property
def norm1(self):
"""nn.Module: normalization layer after the first convolution layer"""
return getattr(self, self.norm1_name)
@property
def norm2(self):
"""nn.Module: normalization layer after the second convolution layer"""
return getattr(self, self.norm2_name)
@property
def norm3(self):
"""nn.Module: normalization layer after the third convolution layer"""
return getattr(self, self.norm3_name)
def forward(self, x):
"""Forward function."""
def _inner_forward(x):
identity = x
out = self.conv1(x)
out = self.norm1(out)
out = self.relu(out)
if self.with_plugins:
out = self.forward_plugin(out, self.after_conv1_plugin_names)
out = self.conv2(out)
out = self.norm2(out)
out = self.relu(out)
if self.with_plugins:
out = self.forward_plugin(out, self.after_conv2_plugin_names)
out = self.conv3(out)
out = self.norm3(out)
if self.with_plugins:
out = self.forward_plugin(out, self.after_conv3_plugin_names)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
return out
if self.with_cp and x.requires_grad:
out = cp.checkpoint(_inner_forward, x)
else:
out = _inner_forward(x)
out = self.relu(out)
return out
@BACKBONES.register_module()
class ResNet(nn.Module):
"""ResNet backbone.
Args:
depth (int): Depth of resnet, from {18, 34, 50, 101, 152}.
in_channels (int): Number of input image channels. Default" 3.
stem_channels (int): Number of stem channels. Default: 64.
base_channels (int): Number of base channels of res layer. Default: 64.
num_stages (int): Resnet stages, normally 4.
strides (Sequence[int]): Strides of the first block of each stage.
dilations (Sequence[int]): Dilation of each stage.
out_indices (Sequence[int]): Output from which stages.
style (str): `pytorch` or `caffe`. If set to "pytorch", the stride-two
layer is the 3x3 conv layer, otherwise the stride-two layer is
the first 1x1 conv layer.
deep_stem (bool): Replace 7x7 conv in input stem with 3 3x3 conv
avg_down (bool): Use AvgPool instead of stride conv when
downsampling in the bottleneck.
frozen_stages (int): Stages to be frozen (stop grad and set eval mode).
-1 means not freezing any parameters.
norm_cfg (dict): Dictionary to construct and config norm layer.
norm_eval (bool): Whether to set norm layers to eval mode, namely,
freeze running stats (mean and var). Note: Effect on Batch Norm
and its variants only.
plugins (list[dict]): List of plugins for stages, each dict contains:
- cfg (dict, required): Cfg dict to build plugin.
- position (str, required): Position inside block to insert plugin,
options: 'after_conv1', 'after_conv2', 'after_conv3'.
- stages (tuple[bool], optional): Stages to apply plugin, length
should be same as 'num_stages'
multi_grid (Sequence[int]|None): Multi grid dilation rates of last
stage. Default: None
contract_dilation (bool): Whether contract first dilation of each layer
Default: False
with_cp (bool): Use checkpoint or not. Using checkpoint will save some
memory while slowing down the training speed.
zero_init_residual (bool): Whether to use zero init for last norm layer
in resblocks to let them behave as identity.
Example:
>>> from annotator.mmpkg.mmseg.models import ResNet
>>> import torch
>>> self = ResNet(depth=18)
>>> self.eval()
>>> inputs = torch.rand(1, 3, 32, 32)
>>> level_outputs = self.forward(inputs)
>>> for level_out in level_outputs:
... print(tuple(level_out.shape))
(1, 64, 8, 8)
(1, 128, 4, 4)
(1, 256, 2, 2)
(1, 512, 1, 1)
"""
arch_settings = {
18: (BasicBlock, (2, 2, 2, 2)),
34: (BasicBlock, (3, 4, 6, 3)),
50: (Bottleneck, (3, 4, 6, 3)),
101: (Bottleneck, (3, 4, 23, 3)),
152: (Bottleneck, (3, 8, 36, 3))
}
def __init__(self,
depth,
in_channels=3,
stem_channels=64,
base_channels=64,
num_stages=4,
strides=(1, 2, 2, 2),
dilations=(1, 1, 1, 1),
out_indices=(0, 1, 2, 3),
style='pytorch',
deep_stem=False,
avg_down=False,
frozen_stages=-1,
conv_cfg=None,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=False,
dcn=None,
stage_with_dcn=(False, False, False, False),
plugins=None,
multi_grid=None,
contract_dilation=False,
with_cp=False,
zero_init_residual=True):
super(ResNet, self).__init__()
if depth not in self.arch_settings:
raise KeyError(f'invalid depth {depth} for resnet')
self.depth = depth
self.stem_channels = stem_channels
self.base_channels = base_channels
self.num_stages = num_stages
assert num_stages >= 1 and num_stages <= 4
self.strides = strides
self.dilations = dilations
assert len(strides) == len(dilations) == num_stages
self.out_indices = out_indices
assert max(out_indices) < num_stages
self.style = style
self.deep_stem = deep_stem
self.avg_down = avg_down
self.frozen_stages = frozen_stages
self.conv_cfg = conv_cfg
self.norm_cfg = norm_cfg
self.with_cp = with_cp
self.norm_eval = norm_eval
self.dcn = dcn
self.stage_with_dcn = stage_with_dcn
if dcn is not None:
assert len(stage_with_dcn) == num_stages
self.plugins = plugins
self.multi_grid = multi_grid
self.contract_dilation = contract_dilation
self.zero_init_residual = zero_init_residual
self.block, stage_blocks = self.arch_settings[depth]
self.stage_blocks = stage_blocks[:num_stages]
self.inplanes = stem_channels
self._make_stem_layer(in_channels, stem_channels)
self.res_layers = []
for i, num_blocks in enumerate(self.stage_blocks):
stride = strides[i]
dilation = dilations[i]
dcn = self.dcn if self.stage_with_dcn[i] else None
if plugins is not None:
stage_plugins = self.make_stage_plugins(plugins, i)
else:
stage_plugins = None
# multi grid is applied to last layer only
stage_multi_grid = multi_grid if i == len(
self.stage_blocks) - 1 else None
planes = base_channels * 2**i
res_layer = self.make_res_layer(
block=self.block,
inplanes=self.inplanes,
planes=planes,
num_blocks=num_blocks,
stride=stride,
dilation=dilation,
style=self.style,
avg_down=self.avg_down,
with_cp=with_cp,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
dcn=dcn,
plugins=stage_plugins,
multi_grid=stage_multi_grid,
contract_dilation=contract_dilation)
self.inplanes = planes * self.block.expansion
layer_name = f'layer{i+1}'
self.add_module(layer_name, res_layer)
self.res_layers.append(layer_name)
self._freeze_stages()
self.feat_dim = self.block.expansion * base_channels * 2**(
len(self.stage_blocks) - 1)
def make_stage_plugins(self, plugins, stage_idx):
"""make plugins for ResNet 'stage_idx'th stage .
Currently we support to insert 'context_block',
'empirical_attention_block', 'nonlocal_block' into the backbone like
ResNet/ResNeXt. They could be inserted after conv1/conv2/conv3 of
Bottleneck.
An example of plugins format could be :
>>> plugins=[
... dict(cfg=dict(type='xxx', arg1='xxx'),
... stages=(False, True, True, True),
... position='after_conv2'),
... dict(cfg=dict(type='yyy'),
... stages=(True, True, True, True),
... position='after_conv3'),
... dict(cfg=dict(type='zzz', postfix='1'),
... stages=(True, True, True, True),
... position='after_conv3'),
... dict(cfg=dict(type='zzz', postfix='2'),
... stages=(True, True, True, True),
... position='after_conv3')
... ]
>>> self = ResNet(depth=18)
>>> stage_plugins = self.make_stage_plugins(plugins, 0)
>>> assert len(stage_plugins) == 3
Suppose 'stage_idx=0', the structure of blocks in the stage would be:
conv1-> conv2->conv3->yyy->zzz1->zzz2
Suppose 'stage_idx=1', the structure of blocks in the stage would be:
conv1-> conv2->xxx->conv3->yyy->zzz1->zzz2
If stages is missing, the plugin would be applied to all stages.
Args:
plugins (list[dict]): List of plugins cfg to build. The postfix is
required if multiple same type plugins are inserted.
stage_idx (int): Index of stage to build
Returns:
list[dict]: Plugins for current stage
"""
stage_plugins = []
for plugin in plugins:
plugin = plugin.copy()
stages = plugin.pop('stages', None)
assert stages is None or len(stages) == self.num_stages
# whether to insert plugin into current stage
if stages is None or stages[stage_idx]:
stage_plugins.append(plugin)
return stage_plugins
def make_res_layer(self, **kwargs):
"""Pack all blocks in a stage into a ``ResLayer``."""
return ResLayer(**kwargs)
@property
def norm1(self):
"""nn.Module: the normalization layer named "norm1" """
return getattr(self, self.norm1_name)
def _make_stem_layer(self, in_channels, stem_channels):
"""Make stem layer for ResNet."""
if self.deep_stem:
self.stem = nn.Sequential(
build_conv_layer(
self.conv_cfg,
in_channels,
stem_channels // 2,
kernel_size=3,
stride=2,
padding=1,
bias=False),
build_norm_layer(self.norm_cfg, stem_channels // 2)[1],
nn.ReLU(inplace=True),
build_conv_layer(
self.conv_cfg,
stem_channels // 2,
stem_channels // 2,
kernel_size=3,
stride=1,
padding=1,
bias=False),
build_norm_layer(self.norm_cfg, stem_channels // 2)[1],
nn.ReLU(inplace=True),
build_conv_layer(
self.conv_cfg,
stem_channels // 2,
stem_channels,
kernel_size=3,
stride=1,
padding=1,
bias=False),
build_norm_layer(self.norm_cfg, stem_channels)[1],
nn.ReLU(inplace=True))
else:
self.conv1 = build_conv_layer(
self.conv_cfg,
in_channels,
stem_channels,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.norm1_name, norm1 = build_norm_layer(
self.norm_cfg, stem_channels, postfix=1)
self.add_module(self.norm1_name, norm1)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
def _freeze_stages(self):
"""Freeze stages param and norm stats."""
if self.frozen_stages >= 0:
if self.deep_stem:
self.stem.eval()
for param in self.stem.parameters():
param.requires_grad = False
else:
self.norm1.eval()
for m in [self.conv1, self.norm1]:
for param in m.parameters():
param.requires_grad = False
for i in range(1, self.frozen_stages + 1):
m = getattr(self, f'layer{i}')
m.eval()
for param in m.parameters():
param.requires_grad = False
def init_weights(self, pretrained=None):
"""Initialize the weights in backbone.
Args:
pretrained (str, optional): Path to pre-trained weights.
Defaults to None.
"""
if isinstance(pretrained, str):
logger = get_root_logger()
load_checkpoint(self, pretrained, strict=False, logger=logger)
elif pretrained is None:
for m in self.modules():
if isinstance(m, nn.Conv2d):
kaiming_init(m)
elif isinstance(m, (_BatchNorm, nn.GroupNorm)):
constant_init(m, 1)
if self.dcn is not None:
for m in self.modules():
if isinstance(m, Bottleneck) and hasattr(
m, 'conv2_offset'):
constant_init(m.conv2_offset, 0)
if self.zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
constant_init(m.norm3, 0)
elif isinstance(m, BasicBlock):
constant_init(m.norm2, 0)
else:
raise TypeError('pretrained must be a str or None')
def forward(self, x):
"""Forward function."""
if self.deep_stem:
x = self.stem(x)
else:
x = self.conv1(x)
x = self.norm1(x)
x = self.relu(x)
x = self.maxpool(x)
outs = []
for i, layer_name in enumerate(self.res_layers):
res_layer = getattr(self, layer_name)
x = res_layer(x)
if i in self.out_indices:
outs.append(x)
return tuple(outs)
def train(self, mode=True):
"""Convert the model into training mode while keep normalization layer
freezed."""
super(ResNet, self).train(mode)
self._freeze_stages()
if mode and self.norm_eval:
for m in self.modules():
# trick: eval have effect on BatchNorm only
if isinstance(m, _BatchNorm):
m.eval()
@BACKBONES.register_module()
class ResNetV1c(ResNet):
"""ResNetV1c variant described in [1]_.
Compared with default ResNet(ResNetV1b), ResNetV1c replaces the 7x7 conv
in the input stem with three 3x3 convs.
References:
.. [1] https://arxiv.org/pdf/1812.01187.pdf
"""
def __init__(self, **kwargs):
super(ResNetV1c, self).__init__(
deep_stem=True, avg_down=False, **kwargs)
@BACKBONES.register_module()
class ResNetV1d(ResNet):
"""ResNetV1d variant described in [1]_.
Compared with default ResNet(ResNetV1b), ResNetV1d replaces the 7x7 conv in
the input stem with three 3x3 convs. And in the downsampling block, a 2x2
avg_pool with stride 2 is added before conv, whose stride is changed to 1.
"""
def __init__(self, **kwargs):
super(ResNetV1d, self).__init__(
deep_stem=True, avg_down=True, **kwargs)
|