Spaces:
Runtime error
Runtime error
File size: 10,763 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 |
# Copyright (c) OpenMMLab. All rights reserved.
from typing import List
import torch
import torch.nn as nn
from mmcv.cnn import ConvModule
from mmdet.utils import ConfigType, OptMultiConfig
from mmyolo.registry import MODELS
from ..layers import BepC3StageBlock, RepStageBlock
from ..utils import make_round
from .base_yolo_neck import BaseYOLONeck
@MODELS.register_module()
class YOLOv6RepPAFPN(BaseYOLONeck):
"""Path Aggregation Network used in YOLOv6.
Args:
in_channels (List[int]): Number of input channels per scale.
out_channels (int): Number of output channels (used at each scale)
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.
num_csp_blocks (int): Number of bottlenecks in CSPLayer. Defaults to 1.
freeze_all(bool): Whether to freeze the model.
norm_cfg (dict): Config dict for normalization layer.
Defaults to dict(type='BN', momentum=0.03, eps=0.001).
act_cfg (dict): Config dict for activation layer.
Defaults to dict(type='ReLU', inplace=True).
block_cfg (dict): Config dict for the block used to build each
layer. Defaults to dict(type='RepVGGBlock').
init_cfg (dict or list[dict], optional): Initialization config dict.
Defaults to None.
"""
def __init__(self,
in_channels: List[int],
out_channels: int,
deepen_factor: float = 1.0,
widen_factor: float = 1.0,
num_csp_blocks: int = 12,
freeze_all: bool = False,
norm_cfg: ConfigType = dict(
type='BN', momentum=0.03, eps=0.001),
act_cfg: ConfigType = dict(type='ReLU', inplace=True),
block_cfg: ConfigType = dict(type='RepVGGBlock'),
init_cfg: OptMultiConfig = None):
self.num_csp_blocks = num_csp_blocks
self.block_cfg = block_cfg
super().__init__(
in_channels=in_channels,
out_channels=out_channels,
deepen_factor=deepen_factor,
widen_factor=widen_factor,
freeze_all=freeze_all,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
init_cfg=init_cfg)
def build_reduce_layer(self, idx: int) -> nn.Module:
"""build reduce layer.
Args:
idx (int): layer idx.
Returns:
nn.Module: The reduce layer.
"""
if idx == 2:
layer = ConvModule(
in_channels=int(self.in_channels[idx] * self.widen_factor),
out_channels=int(self.out_channels[idx - 1] *
self.widen_factor),
kernel_size=1,
stride=1,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
else:
layer = nn.Identity()
return layer
def build_upsample_layer(self, idx: int) -> nn.Module:
"""build upsample layer.
Args:
idx (int): layer idx.
Returns:
nn.Module: The upsample layer.
"""
return nn.ConvTranspose2d(
in_channels=int(self.out_channels[idx - 1] * self.widen_factor),
out_channels=int(self.out_channels[idx - 1] * self.widen_factor),
kernel_size=2,
stride=2,
bias=True)
def build_top_down_layer(self, idx: int) -> nn.Module:
"""build top down layer.
Args:
idx (int): layer idx.
Returns:
nn.Module: The top down layer.
"""
block_cfg = self.block_cfg.copy()
layer0 = RepStageBlock(
in_channels=int(
(self.out_channels[idx - 1] + self.in_channels[idx - 1]) *
self.widen_factor),
out_channels=int(self.out_channels[idx - 1] * self.widen_factor),
num_blocks=make_round(self.num_csp_blocks, self.deepen_factor),
block_cfg=block_cfg)
if idx == 1:
return layer0
elif idx == 2:
layer1 = ConvModule(
in_channels=int(self.out_channels[idx - 1] *
self.widen_factor),
out_channels=int(self.out_channels[idx - 2] *
self.widen_factor),
kernel_size=1,
stride=1,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
return nn.Sequential(layer0, layer1)
def build_downsample_layer(self, idx: int) -> nn.Module:
"""build downsample layer.
Args:
idx (int): layer idx.
Returns:
nn.Module: The downsample layer.
"""
return ConvModule(
in_channels=int(self.out_channels[idx] * self.widen_factor),
out_channels=int(self.out_channels[idx] * self.widen_factor),
kernel_size=3,
stride=2,
padding=3 // 2,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
def build_bottom_up_layer(self, idx: int) -> nn.Module:
"""build bottom up layer.
Args:
idx (int): layer idx.
Returns:
nn.Module: The bottom up layer.
"""
block_cfg = self.block_cfg.copy()
return RepStageBlock(
in_channels=int(self.out_channels[idx] * 2 * self.widen_factor),
out_channels=int(self.out_channels[idx + 1] * self.widen_factor),
num_blocks=make_round(self.num_csp_blocks, self.deepen_factor),
block_cfg=block_cfg)
def build_out_layer(self, *args, **kwargs) -> nn.Module:
"""build out layer."""
return nn.Identity()
def init_weights(self):
if self.init_cfg is None:
"""Initialize the parameters."""
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 YOLOv6CSPRepPAFPN(YOLOv6RepPAFPN):
"""Path Aggregation Network used in YOLOv6.
Args:
in_channels (List[int]): Number of input channels per scale.
out_channels (int): Number of output channels (used at each scale)
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.
num_csp_blocks (int): Number of bottlenecks in CSPLayer. Defaults to 1.
freeze_all(bool): Whether to freeze the model.
norm_cfg (dict): Config dict for normalization layer.
Defaults to dict(type='BN', momentum=0.03, eps=0.001).
act_cfg (dict): Config dict for activation layer.
Defaults to dict(type='ReLU', inplace=True).
block_cfg (dict): Config dict for the block used to build each
layer. Defaults to dict(type='RepVGGBlock').
block_act_cfg (dict): Config dict for activation layer used in each
stage. Defaults to dict(type='SiLU', inplace=True).
init_cfg (dict or list[dict], optional): Initialization config dict.
Defaults to None.
"""
def __init__(self,
in_channels: List[int],
out_channels: int,
deepen_factor: float = 1.0,
widen_factor: float = 1.0,
hidden_ratio: float = 0.5,
num_csp_blocks: int = 12,
freeze_all: bool = False,
norm_cfg: ConfigType = dict(
type='BN', momentum=0.03, eps=0.001),
act_cfg: ConfigType = dict(type='ReLU', inplace=True),
block_act_cfg: ConfigType = dict(type='SiLU', inplace=True),
block_cfg: ConfigType = dict(type='RepVGGBlock'),
init_cfg: OptMultiConfig = None):
self.hidden_ratio = hidden_ratio
self.block_act_cfg = block_act_cfg
super().__init__(
in_channels=in_channels,
out_channels=out_channels,
deepen_factor=deepen_factor,
widen_factor=widen_factor,
num_csp_blocks=num_csp_blocks,
freeze_all=freeze_all,
norm_cfg=norm_cfg,
act_cfg=act_cfg,
block_cfg=block_cfg,
init_cfg=init_cfg)
def build_top_down_layer(self, idx: int) -> nn.Module:
"""build top down layer.
Args:
idx (int): layer idx.
Returns:
nn.Module: The top down layer.
"""
block_cfg = self.block_cfg.copy()
layer0 = BepC3StageBlock(
in_channels=int(
(self.out_channels[idx - 1] + self.in_channels[idx - 1]) *
self.widen_factor),
out_channels=int(self.out_channels[idx - 1] * self.widen_factor),
num_blocks=make_round(self.num_csp_blocks, self.deepen_factor),
block_cfg=block_cfg,
hidden_ratio=self.hidden_ratio,
norm_cfg=self.norm_cfg,
act_cfg=self.block_act_cfg)
if idx == 1:
return layer0
elif idx == 2:
layer1 = ConvModule(
in_channels=int(self.out_channels[idx - 1] *
self.widen_factor),
out_channels=int(self.out_channels[idx - 2] *
self.widen_factor),
kernel_size=1,
stride=1,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
return nn.Sequential(layer0, layer1)
def build_bottom_up_layer(self, idx: int) -> nn.Module:
"""build bottom up layer.
Args:
idx (int): layer idx.
Returns:
nn.Module: The bottom up layer.
"""
block_cfg = self.block_cfg.copy()
return BepC3StageBlock(
in_channels=int(self.out_channels[idx] * 2 * self.widen_factor),
out_channels=int(self.out_channels[idx + 1] * self.widen_factor),
num_blocks=make_round(self.num_csp_blocks, self.deepen_factor),
block_cfg=block_cfg,
hidden_ratio=self.hidden_ratio,
norm_cfg=self.norm_cfg,
act_cfg=self.block_act_cfg)
|