Spaces:
Runtime error
Runtime error
File size: 23,809 Bytes
f549064 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 |
# Copyright (c) OpenMMLab. All rights reserved.
import torch.nn as nn
import torch.utils.checkpoint as cp
from mmcv.cnn import (ConvModule, build_activation_layer, build_conv_layer,
build_norm_layer)
from mmcv.cnn.bricks import DropPath
from mmengine.model import BaseModule
from mmengine.model.weight_init import constant_init
from mmengine.utils.dl_utils.parrots_wrapper import _BatchNorm
from mmcls.registry import MODELS
from .base_backbone import BaseBackbone
eps = 1.0e-5
class BasicBlock(BaseModule):
"""BasicBlock for ResNet.
Args:
in_channels (int): Input channels of this block.
out_channels (int): Output channels of this block.
expansion (int): The ratio of ``out_channels/mid_channels`` where
``mid_channels`` is the output channels of conv1. This is a
reserved argument in BasicBlock and should always be 1. Default: 1.
stride (int): stride of the block. Default: 1
dilation (int): dilation of convolution. Default: 1
downsample (nn.Module, optional): downsample operation on identity
branch. Default: None.
style (str): `pytorch` or `caffe`. It is unused and reserved for
unified API with Bottleneck.
with_cp (bool): Use checkpoint or not. Using checkpoint will save some
memory while slowing down the training speed.
conv_cfg (dict, optional): dictionary to construct and config conv
layer. Default: None
norm_cfg (dict): dictionary to construct and config norm layer.
Default: dict(type='BN')
"""
def __init__(self,
in_channels,
out_channels,
expansion=1,
stride=1,
dilation=1,
downsample=None,
style='pytorch',
with_cp=False,
conv_cfg=None,
norm_cfg=dict(type='BN'),
drop_path_rate=0.0,
act_cfg=dict(type='ReLU', inplace=True),
init_cfg=None):
super(BasicBlock, self).__init__(init_cfg=init_cfg)
self.in_channels = in_channels
self.out_channels = out_channels
self.expansion = expansion
assert self.expansion == 1
assert out_channels % expansion == 0
self.mid_channels = out_channels // expansion
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.norm1_name, norm1 = build_norm_layer(
norm_cfg, self.mid_channels, postfix=1)
self.norm2_name, norm2 = build_norm_layer(
norm_cfg, out_channels, postfix=2)
self.conv1 = build_conv_layer(
conv_cfg,
in_channels,
self.mid_channels,
3,
stride=stride,
padding=dilation,
dilation=dilation,
bias=False)
self.add_module(self.norm1_name, norm1)
self.conv2 = build_conv_layer(
conv_cfg,
self.mid_channels,
out_channels,
3,
padding=1,
bias=False)
self.add_module(self.norm2_name, norm2)
self.relu = build_activation_layer(act_cfg)
self.downsample = downsample
self.drop_path = DropPath(drop_prob=drop_path_rate
) if drop_path_rate > eps else nn.Identity()
@property
def norm1(self):
return getattr(self, self.norm1_name)
@property
def norm2(self):
return getattr(self, self.norm2_name)
def forward(self, x):
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 = self.drop_path(out)
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(BaseModule):
"""Bottleneck block for ResNet.
Args:
in_channels (int): Input channels of this block.
out_channels (int): Output channels of this block.
expansion (int): The ratio of ``out_channels/mid_channels`` where
``mid_channels`` is the input/output channels of conv2. Default: 4.
stride (int): stride of the block. Default: 1
dilation (int): dilation of convolution. Default: 1
downsample (nn.Module, optional): downsample operation on identity
branch. Default: None.
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. Default: "pytorch".
with_cp (bool): Use checkpoint or not. Using checkpoint will save some
memory while slowing down the training speed.
conv_cfg (dict, optional): dictionary to construct and config conv
layer. Default: None
norm_cfg (dict): dictionary to construct and config norm layer.
Default: dict(type='BN')
"""
def __init__(self,
in_channels,
out_channels,
expansion=4,
stride=1,
dilation=1,
downsample=None,
style='pytorch',
with_cp=False,
conv_cfg=None,
norm_cfg=dict(type='BN'),
act_cfg=dict(type='ReLU', inplace=True),
drop_path_rate=0.0,
init_cfg=None):
super(Bottleneck, self).__init__(init_cfg=init_cfg)
assert style in ['pytorch', 'caffe']
self.in_channels = in_channels
self.out_channels = out_channels
self.expansion = expansion
assert out_channels % expansion == 0
self.mid_channels = out_channels // expansion
self.stride = stride
self.dilation = dilation
self.style = style
self.with_cp = with_cp
self.conv_cfg = conv_cfg
self.norm_cfg = norm_cfg
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, self.mid_channels, postfix=1)
self.norm2_name, norm2 = build_norm_layer(
norm_cfg, self.mid_channels, postfix=2)
self.norm3_name, norm3 = build_norm_layer(
norm_cfg, out_channels, postfix=3)
self.conv1 = build_conv_layer(
conv_cfg,
in_channels,
self.mid_channels,
kernel_size=1,
stride=self.conv1_stride,
bias=False)
self.add_module(self.norm1_name, norm1)
self.conv2 = build_conv_layer(
conv_cfg,
self.mid_channels,
self.mid_channels,
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,
self.mid_channels,
out_channels,
kernel_size=1,
bias=False)
self.add_module(self.norm3_name, norm3)
self.relu = build_activation_layer(act_cfg)
self.downsample = downsample
self.drop_path = DropPath(drop_prob=drop_path_rate
) if drop_path_rate > eps else nn.Identity()
@property
def norm1(self):
return getattr(self, self.norm1_name)
@property
def norm2(self):
return getattr(self, self.norm2_name)
@property
def norm3(self):
return getattr(self, self.norm3_name)
def forward(self, x):
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)
out = self.relu(out)
out = self.conv3(out)
out = self.norm3(out)
if self.downsample is not None:
identity = self.downsample(x)
out = self.drop_path(out)
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
def get_expansion(block, expansion=None):
"""Get the expansion of a residual block.
The block expansion will be obtained by the following order:
1. If ``expansion`` is given, just return it.
2. If ``block`` has the attribute ``expansion``, then return
``block.expansion``.
3. Return the default value according the the block type:
1 for ``BasicBlock`` and 4 for ``Bottleneck``.
Args:
block (class): The block class.
expansion (int | None): The given expansion ratio.
Returns:
int: The expansion of the block.
"""
if isinstance(expansion, int):
assert expansion > 0
elif expansion is None:
if hasattr(block, 'expansion'):
expansion = block.expansion
elif issubclass(block, BasicBlock):
expansion = 1
elif issubclass(block, Bottleneck):
expansion = 4
else:
raise TypeError(f'expansion is not specified for {block.__name__}')
else:
raise TypeError('expansion must be an integer or None')
return expansion
class ResLayer(nn.Sequential):
"""ResLayer to build ResNet style backbone.
Args:
block (nn.Module): Residual block used to build ResLayer.
num_blocks (int): Number of blocks.
in_channels (int): Input channels of this block.
out_channels (int): Output channels of this block.
expansion (int, optional): The expansion for BasicBlock/Bottleneck.
If not specified, it will firstly be obtained via
``block.expansion``. If the block has no attribute "expansion",
the following default values will be used: 1 for BasicBlock and
4 for Bottleneck. Default: None.
stride (int): stride of the first block. Default: 1.
avg_down (bool): Use AvgPool instead of stride conv when
downsampling in the bottleneck. Default: False
conv_cfg (dict, optional): dictionary to construct and config conv
layer. Default: None
norm_cfg (dict): dictionary to construct and config norm layer.
Default: dict(type='BN')
"""
def __init__(self,
block,
num_blocks,
in_channels,
out_channels,
expansion=None,
stride=1,
avg_down=False,
conv_cfg=None,
norm_cfg=dict(type='BN'),
**kwargs):
self.block = block
self.expansion = get_expansion(block, expansion)
downsample = None
if stride != 1 or in_channels != out_channels:
downsample = []
conv_stride = stride
if avg_down and stride != 1:
conv_stride = 1
downsample.append(
nn.AvgPool2d(
kernel_size=stride,
stride=stride,
ceil_mode=True,
count_include_pad=False))
downsample.extend([
build_conv_layer(
conv_cfg,
in_channels,
out_channels,
kernel_size=1,
stride=conv_stride,
bias=False),
build_norm_layer(norm_cfg, out_channels)[1]
])
downsample = nn.Sequential(*downsample)
layers = []
layers.append(
block(
in_channels=in_channels,
out_channels=out_channels,
expansion=self.expansion,
stride=stride,
downsample=downsample,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
**kwargs))
in_channels = out_channels
for i in range(1, num_blocks):
layers.append(
block(
in_channels=in_channels,
out_channels=out_channels,
expansion=self.expansion,
stride=1,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
**kwargs))
super(ResLayer, self).__init__(*layers)
@MODELS.register_module()
class ResNet(BaseBackbone):
"""ResNet backbone.
Please refer to the `paper <https://arxiv.org/abs/1512.03385>`__ for
details.
Args:
depth (int): Network depth, from {18, 34, 50, 101, 152}.
in_channels (int): Number of input image channels. Default: 3.
stem_channels (int): Output channels of the stem layer. Default: 64.
base_channels (int): Middle channels of the first stage. Default: 64.
num_stages (int): Stages of the network. Default: 4.
strides (Sequence[int]): Strides of the first block of each stage.
Default: ``(1, 2, 2, 2)``.
dilations (Sequence[int]): Dilation of each stage.
Default: ``(1, 1, 1, 1)``.
out_indices (Sequence[int]): Output from which stages.
Default: ``(3, )``.
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.
Default: False.
avg_down (bool): Use AvgPool instead of stride conv when
downsampling in the bottleneck. Default: False.
frozen_stages (int): Stages to be frozen (stop grad and set eval mode).
-1 means not freezing any parameters. Default: -1.
conv_cfg (dict | None): The config dict for conv layers. Default: None.
norm_cfg (dict): The config dict for norm layers.
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. Default: False.
with_cp (bool): Use checkpoint or not. Using checkpoint will save some
memory while slowing down the training speed. Default: False.
zero_init_residual (bool): Whether to use zero init for last norm layer
in resblocks to let them behave as identity. Default: True.
Example:
>>> from mmcls.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,
expansion=None,
num_stages=4,
strides=(1, 2, 2, 2),
dilations=(1, 1, 1, 1),
out_indices=(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,
with_cp=False,
zero_init_residual=True,
init_cfg=[
dict(type='Kaiming', layer=['Conv2d']),
dict(
type='Constant',
val=1,
layer=['_BatchNorm', 'GroupNorm'])
],
drop_path_rate=0.0):
super(ResNet, self).__init__(init_cfg)
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.zero_init_residual = zero_init_residual
self.block, stage_blocks = self.arch_settings[depth]
self.stage_blocks = stage_blocks[:num_stages]
self.expansion = get_expansion(self.block, expansion)
self._make_stem_layer(in_channels, stem_channels)
self.res_layers = []
_in_channels = stem_channels
_out_channels = base_channels * self.expansion
for i, num_blocks in enumerate(self.stage_blocks):
stride = strides[i]
dilation = dilations[i]
res_layer = self.make_res_layer(
block=self.block,
num_blocks=num_blocks,
in_channels=_in_channels,
out_channels=_out_channels,
expansion=self.expansion,
stride=stride,
dilation=dilation,
style=self.style,
avg_down=self.avg_down,
with_cp=with_cp,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
drop_path_rate=drop_path_rate)
_in_channels = _out_channels
_out_channels *= 2
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 = res_layer[-1].out_channels
def make_res_layer(self, **kwargs):
return ResLayer(**kwargs)
@property
def norm1(self):
return getattr(self, self.norm1_name)
def _make_stem_layer(self, in_channels, stem_channels):
if self.deep_stem:
self.stem = nn.Sequential(
ConvModule(
in_channels,
stem_channels // 2,
kernel_size=3,
stride=2,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
inplace=True),
ConvModule(
stem_channels // 2,
stem_channels // 2,
kernel_size=3,
stride=1,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
inplace=True),
ConvModule(
stem_channels // 2,
stem_channels,
kernel_size=3,
stride=1,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
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):
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):
super(ResNet, self).init_weights()
if (isinstance(self.init_cfg, dict)
and self.init_cfg['type'] == 'Pretrained'):
# Suppress zero_init_residual if use pretrained model.
return
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)
def forward(self, x):
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):
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()
@MODELS.register_module()
class ResNetV1c(ResNet):
"""ResNetV1c backbone.
This variant is described in `Bag of Tricks.
<https://arxiv.org/pdf/1812.01187.pdf>`_.
Compared with default ResNet(ResNetV1b), ResNetV1c replaces the 7x7 conv
in the input stem with three 3x3 convs.
"""
def __init__(self, **kwargs):
super(ResNetV1c, self).__init__(
deep_stem=True, avg_down=False, **kwargs)
@MODELS.register_module()
class ResNetV1d(ResNet):
"""ResNetV1d backbone.
This variant is described in `Bag of Tricks.
<https://arxiv.org/pdf/1812.01187.pdf>`_.
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)
|