Spaces:
Runtime error
Runtime error
File size: 17,158 Bytes
3094730 |
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 |
# Copyright (c) OpenMMLab. All rights reserved.
from typing import List, Tuple, Union
import torch
import torch.nn as nn
from mmcv.cnn import ConvModule, DepthwiseSeparableConvModule
from mmdet.models.backbones.csp_darknet import CSPLayer, Focus
from mmdet.utils import ConfigType, OptMultiConfig
from mmyolo.registry import MODELS
from ..layers import CSPLayerWithTwoConv, SPPFBottleneck
from ..utils import make_divisible, make_round
from .base_backbone import BaseBackbone
@MODELS.register_module()
class YOLOv5CSPDarknet(BaseBackbone):
"""CSP-Darknet backbone used in YOLOv5.
Args:
arch (str): Architecture of CSP-Darknet, from {P5, P6}.
Defaults to P5.
plugins (list[dict]): List of plugins for stages, each dict contains:
- cfg (dict, required): Cfg dict to build plugin.
- stages (tuple[bool], optional): Stages to apply plugin, length
should be same as 'num_stages'.
deepen_factor (float): Depth multiplier, multiply number of
blocks in CSP layer by this amount. Defaults to 1.0.
widen_factor (float): Width multiplier, multiply number of
channels in each layer by this amount. Defaults to 1.0.
input_channels (int): Number of input image channels. Defaults to: 3.
out_indices (Tuple[int]): Output from which stages.
Defaults to (2, 3, 4).
frozen_stages (int): Stages to be frozen (stop grad and set eval
mode). -1 means not freezing any parameters. Defaults to -1.
norm_cfg (dict): Dictionary to construct and config norm layer.
Defaults to dict(type='BN', requires_grad=True).
act_cfg (dict): Config dict for activation layer.
Defaults to dict(type='SiLU', inplace=True).
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. Defaults to False.
init_cfg (Union[dict,list[dict]], optional): Initialization config
dict. Defaults to None.
Example:
>>> from mmyolo.models import YOLOv5CSPDarknet
>>> import torch
>>> model = YOLOv5CSPDarknet()
>>> model.eval()
>>> inputs = torch.rand(1, 3, 416, 416)
>>> level_outputs = model(inputs)
>>> for level_out in level_outputs:
... print(tuple(level_out.shape))
...
(1, 256, 52, 52)
(1, 512, 26, 26)
(1, 1024, 13, 13)
"""
# From left to right:
# in_channels, out_channels, num_blocks, add_identity, use_spp
arch_settings = {
'P5': [[64, 128, 3, True, False], [128, 256, 6, True, False],
[256, 512, 9, True, False], [512, 1024, 3, True, True]],
'P6': [[64, 128, 3, True, False], [128, 256, 6, True, False],
[256, 512, 9, True, False], [512, 768, 3, True, False],
[768, 1024, 3, True, True]]
}
def __init__(self,
arch: str = 'P5',
plugins: Union[dict, List[dict]] = None,
deepen_factor: float = 1.0,
widen_factor: float = 1.0,
input_channels: int = 3,
out_indices: Tuple[int] = (2, 3, 4),
frozen_stages: int = -1,
norm_cfg: ConfigType = dict(
type='BN', momentum=0.03, eps=0.001),
act_cfg: ConfigType = dict(type='SiLU', inplace=True),
norm_eval: bool = False,
init_cfg: OptMultiConfig = None):
super().__init__(
self.arch_settings[arch],
deepen_factor,
widen_factor,
input_channels=input_channels,
out_indices=out_indices,
plugins=plugins,
frozen_stages=frozen_stages,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
norm_eval=norm_eval,
init_cfg=init_cfg)
def build_stem_layer(self) -> nn.Module:
"""Build a stem layer."""
return ConvModule(
self.input_channels,
make_divisible(self.arch_setting[0][0], self.widen_factor),
kernel_size=6,
stride=2,
padding=2,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
def build_stage_layer(self, stage_idx: int, setting: list) -> list:
"""Build a stage layer.
Args:
stage_idx (int): The index of a stage layer.
setting (list): The architecture setting of a stage layer.
"""
in_channels, out_channels, num_blocks, add_identity, use_spp = setting
in_channels = make_divisible(in_channels, self.widen_factor)
out_channels = make_divisible(out_channels, self.widen_factor)
num_blocks = make_round(num_blocks, self.deepen_factor)
stage = []
conv_layer = ConvModule(
in_channels,
out_channels,
kernel_size=3,
stride=2,
padding=1,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
stage.append(conv_layer)
csp_layer = CSPLayer(
out_channels,
out_channels,
num_blocks=num_blocks,
add_identity=add_identity,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
stage.append(csp_layer)
if use_spp:
spp = SPPFBottleneck(
out_channels,
out_channels,
kernel_sizes=5,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
stage.append(spp)
return stage
def init_weights(self):
"""Initialize the parameters."""
if self.init_cfg is None:
for m in self.modules():
if isinstance(m, torch.nn.Conv2d):
# In order to be consistent with the source code,
# reset the Conv2d initialization parameters
m.reset_parameters()
else:
super().init_weights()
@MODELS.register_module()
class YOLOv8CSPDarknet(BaseBackbone):
"""CSP-Darknet backbone used in YOLOv8.
Args:
arch (str): Architecture of CSP-Darknet, from {P5}.
Defaults to P5.
last_stage_out_channels (int): Final layer output channel.
Defaults to 1024.
plugins (list[dict]): List of plugins for stages, each dict contains:
- cfg (dict, required): Cfg dict to build plugin.
- stages (tuple[bool], optional): Stages to apply plugin, length
should be same as 'num_stages'.
deepen_factor (float): Depth multiplier, multiply number of
blocks in CSP layer by this amount. Defaults to 1.0.
widen_factor (float): Width multiplier, multiply number of
channels in each layer by this amount. Defaults to 1.0.
input_channels (int): Number of input image channels. Defaults to: 3.
out_indices (Tuple[int]): Output from which stages.
Defaults to (2, 3, 4).
frozen_stages (int): Stages to be frozen (stop grad and set eval
mode). -1 means not freezing any parameters. Defaults to -1.
norm_cfg (dict): Dictionary to construct and config norm layer.
Defaults to dict(type='BN', requires_grad=True).
act_cfg (dict): Config dict for activation layer.
Defaults to dict(type='SiLU', inplace=True).
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. Defaults to False.
init_cfg (Union[dict,list[dict]], optional): Initialization config
dict. Defaults to None.
Example:
>>> from mmyolo.models import YOLOv8CSPDarknet
>>> import torch
>>> model = YOLOv8CSPDarknet()
>>> model.eval()
>>> inputs = torch.rand(1, 3, 416, 416)
>>> level_outputs = model(inputs)
>>> for level_out in level_outputs:
... print(tuple(level_out.shape))
...
(1, 256, 52, 52)
(1, 512, 26, 26)
(1, 1024, 13, 13)
"""
# From left to right:
# in_channels, out_channels, num_blocks, add_identity, use_spp
# the final out_channels will be set according to the param.
arch_settings = {
'P5': [[64, 128, 3, True, False], [128, 256, 6, True, False],
[256, 512, 6, True, False], [512, None, 3, True, True]],
}
def __init__(self,
arch: str = 'P5',
last_stage_out_channels: int = 1024,
plugins: Union[dict, List[dict]] = None,
deepen_factor: float = 1.0,
widen_factor: float = 1.0,
input_channels: int = 3,
out_indices: Tuple[int] = (2, 3, 4),
frozen_stages: int = -1,
norm_cfg: ConfigType = dict(
type='BN', momentum=0.03, eps=0.001),
act_cfg: ConfigType = dict(type='SiLU', inplace=True),
norm_eval: bool = False,
init_cfg: OptMultiConfig = None):
self.arch_settings[arch][-1][1] = last_stage_out_channels
super().__init__(
self.arch_settings[arch],
deepen_factor,
widen_factor,
input_channels=input_channels,
out_indices=out_indices,
plugins=plugins,
frozen_stages=frozen_stages,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
norm_eval=norm_eval,
init_cfg=init_cfg)
def build_stem_layer(self) -> nn.Module:
"""Build a stem layer."""
return ConvModule(
self.input_channels,
make_divisible(self.arch_setting[0][0], self.widen_factor),
kernel_size=3,
stride=2,
padding=1,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
def build_stage_layer(self, stage_idx: int, setting: list) -> list:
"""Build a stage layer.
Args:
stage_idx (int): The index of a stage layer.
setting (list): The architecture setting of a stage layer.
"""
in_channels, out_channels, num_blocks, add_identity, use_spp = setting
in_channels = make_divisible(in_channels, self.widen_factor)
out_channels = make_divisible(out_channels, self.widen_factor)
num_blocks = make_round(num_blocks, self.deepen_factor)
stage = []
conv_layer = ConvModule(
in_channels,
out_channels,
kernel_size=3,
stride=2,
padding=1,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
stage.append(conv_layer)
csp_layer = CSPLayerWithTwoConv(
out_channels,
out_channels,
num_blocks=num_blocks,
add_identity=add_identity,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
stage.append(csp_layer)
if use_spp:
spp = SPPFBottleneck(
out_channels,
out_channels,
kernel_sizes=5,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
stage.append(spp)
return stage
def init_weights(self):
"""Initialize the parameters."""
if self.init_cfg is None:
for m in self.modules():
if isinstance(m, torch.nn.Conv2d):
# In order to be consistent with the source code,
# reset the Conv2d initialization parameters
m.reset_parameters()
else:
super().init_weights()
@MODELS.register_module()
class YOLOXCSPDarknet(BaseBackbone):
"""CSP-Darknet backbone used in YOLOX.
Args:
arch (str): Architecture of CSP-Darknet, from {P5, P6}.
Defaults to P5.
plugins (list[dict]): List of plugins for stages, each dict contains:
- cfg (dict, required): Cfg dict to build plugin.
- stages (tuple[bool], optional): Stages to apply plugin, length
should be same as 'num_stages'.
deepen_factor (float): Depth multiplier, multiply number of
blocks in CSP layer by this amount. Defaults to 1.0.
widen_factor (float): Width multiplier, multiply number of
channels in each layer by this amount. Defaults to 1.0.
input_channels (int): Number of input image channels. Defaults to 3.
out_indices (Tuple[int]): Output from which stages.
Defaults to (2, 3, 4).
frozen_stages (int): Stages to be frozen (stop grad and set eval
mode). -1 means not freezing any parameters. Defaults to -1.
use_depthwise (bool): Whether to use depthwise separable convolution.
Defaults to False.
spp_kernal_sizes: (tuple[int]): Sequential of kernel sizes of SPP
layers. Defaults to (5, 9, 13).
norm_cfg (dict): Dictionary to construct and config norm layer.
Defaults to dict(type='BN', momentum=0.03, eps=0.001).
act_cfg (dict): Config dict for activation layer.
Defaults to dict(type='SiLU', inplace=True).
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.
init_cfg (Union[dict,list[dict]], optional): Initialization config
dict. Defaults to None.
Example:
>>> from mmyolo.models import YOLOXCSPDarknet
>>> import torch
>>> model = YOLOXCSPDarknet()
>>> model.eval()
>>> inputs = torch.rand(1, 3, 416, 416)
>>> level_outputs = model(inputs)
>>> for level_out in level_outputs:
... print(tuple(level_out.shape))
...
(1, 256, 52, 52)
(1, 512, 26, 26)
(1, 1024, 13, 13)
"""
# From left to right:
# in_channels, out_channels, num_blocks, add_identity, use_spp
arch_settings = {
'P5': [[64, 128, 3, True, False], [128, 256, 9, True, False],
[256, 512, 9, True, False], [512, 1024, 3, False, True]],
}
def __init__(self,
arch: str = 'P5',
plugins: Union[dict, List[dict]] = None,
deepen_factor: float = 1.0,
widen_factor: float = 1.0,
input_channels: int = 3,
out_indices: Tuple[int] = (2, 3, 4),
frozen_stages: int = -1,
use_depthwise: bool = False,
spp_kernal_sizes: Tuple[int] = (5, 9, 13),
norm_cfg: ConfigType = dict(
type='BN', momentum=0.03, eps=0.001),
act_cfg: ConfigType = dict(type='SiLU', inplace=True),
norm_eval: bool = False,
init_cfg: OptMultiConfig = None):
self.use_depthwise = use_depthwise
self.spp_kernal_sizes = spp_kernal_sizes
super().__init__(self.arch_settings[arch], deepen_factor, widen_factor,
input_channels, out_indices, frozen_stages, plugins,
norm_cfg, act_cfg, norm_eval, init_cfg)
def build_stem_layer(self) -> nn.Module:
"""Build a stem layer."""
return Focus(
3,
make_divisible(64, self.widen_factor),
kernel_size=3,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
def build_stage_layer(self, stage_idx: int, setting: list) -> list:
"""Build a stage layer.
Args:
stage_idx (int): The index of a stage layer.
setting (list): The architecture setting of a stage layer.
"""
in_channels, out_channels, num_blocks, add_identity, use_spp = setting
in_channels = make_divisible(in_channels, self.widen_factor)
out_channels = make_divisible(out_channels, self.widen_factor)
num_blocks = make_round(num_blocks, self.deepen_factor)
stage = []
conv = DepthwiseSeparableConvModule \
if self.use_depthwise else ConvModule
conv_layer = conv(
in_channels,
out_channels,
kernel_size=3,
stride=2,
padding=1,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
stage.append(conv_layer)
if use_spp:
spp = SPPFBottleneck(
out_channels,
out_channels,
kernel_sizes=self.spp_kernal_sizes,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
stage.append(spp)
csp_layer = CSPLayer(
out_channels,
out_channels,
num_blocks=num_blocks,
add_identity=add_identity,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
stage.append(csp_layer)
return stage
|