热门标签
热门文章
- 1基于知识图谱的医疗知识问答系统_基于医疗知识图谱的问答研究论文
- 2街头霸王5显示正在登陆服务器无法进入游戏,街头霸王5打不开怎么办 无法进入游戏解决方法...
- 3BigScience bloom模型
- 4毕业于二本的00后，学习一年后就职阿里网络安全工程师，年薪20W_二本计科转网络安全
- 5Modelsim仿真图中添加内部信号到wave_modelsim怎么添加内部信号
- 6完整版C语言贪吃蛇代码_贪吃蛇worm代码解释
- 7diffusion model原理和算法伪代码_diffusion loss
- 8前端-Axure RP9 的使用（二）_axure页面拉伸
- 9C语言数据结构_数据结构c语言
- 10Eclipse的CDT插件配置_eclipse cdt
当前位置: article > 正文
yolov5魔改——ECVblock
作者：笔触狂放9 | 2024-03-29 09:08:23
赞
踩
yolov5魔改
添加ECVBlock
1.ECVBlock模块的作用
ECVBlock模块的主要作用是将特征金字塔中的特征分配到不同的目标上，以便更好地检测不同大小的目标。它通过计算每个目标的大小、形状和位置等信息，为每个目标分配一个感兴趣区域（ROI），并将这些ROI与特征金字塔中的特征进行加权融合，以便更好地检测不同大小的目标。
2.网络内特征金字塔
网络内特征金字塔是YOLOv5中使用的一种特征提取方法。它将输入图像分成多个尺度的特征图，并在每个尺度上使用卷积层进行特征提取。这种方法可以有效地捕捉不同尺度的目标信息，并提高目标检测的准确性和速度。
3.为目标分配ROI
在ECVBlock模块中，首先需要为目标分配ROI。ROI是指感兴趣的区域，它是根据目标的大小、形状和位置等信息计算出来的。对于较小的目标，可以使用较大的ROI；对于较大的目标，可以使用较小的ROI。这样可以确保小目标不会被大目标所掩盖，同时也可以在不同的尺度上检测到不同大小的目标。
4.将ROI与特征金字塔中的特征进行加权融合
一旦为目标分配了ROI，就需要将这些ROI与特征金字塔中的特征进行加权融合。具体来说，就是将每个ROI与特征金字塔中对应尺度的特征进行加权平均，得到一个新的特征向量。这个新的特征向量可以更好地表示目标的信息，并提高目标检测的准确性和速度。
ECVBlock模块是YOLOv5中的一个重要组件，它可以将特征金字塔中的特征分配到不同的目标上，以便更好地检测不同大小的目标。通过计算每个目标的大小、形状和位置等信息，为每个目标分配一个感兴趣区域（ROI），并将这些ROI与特征金字塔中的特征进行加权融合，可以提高目标检测的准确性和速度。
1.在common.py中添加ECVblock
可以直接复制以下代码
#!/usr/bin/env python
# -*- encoding: utf-8 -*-
# Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
import torch
import torch.nn as nn
from torch.nn import functional as F
from .Functions import Encoding, Mean, DropPath, Mlp, GroupNorm, LayerNormChannel, ConvBlock
class SiLU(nn.Module):
"""export-friendly version of nn.SiLU()"""
@staticmethod
def forward(x):
return x * torch.sigmoid(x)
def get_activation(name="silu", inplace=True):
if name == "silu":
module = nn.SiLU(inplace=inplace)
elif name == "relu":
module = nn.ReLU(inplace=inplace)
elif name == "lrelu":
module = nn.LeakyReLU(0.1, inplace=inplace)
else:
raise AttributeError("Unsupported act type: {}".format(name))
return module
class BaseConv(nn.Module):
"""A Conv2d -> Batchnorm -> silu/leaky relu block""" # CBL
def __init__(
self, in_channels, out_channels, ksize, stride, groups=1, bias=False, act="silu"
):
super().__init__()
# same padding
pad = (ksize - 1) // 2
self.conv = nn.Conv2d(
in_channels,
out_channels,
kernel_size=ksize,
stride=stride,
padding=pad,
groups=groups,
bias=bias,
)
self.bn = nn.BatchNorm2d(out_channels)
self.act = get_activation(act, inplace=True)
def forward(self, x):
return self.act(self.bn(self.conv(x)))
def fuseforward(self, x):
return self.act(self.conv(x))
class DWConv(nn.Module):
"""Depthwise Conv + Conv"""
def __init__(self, in_channels, out_channels, ksize, stride=1, act="silu"):
super().__init__()
self.dconv = BaseConv(
in_channels,
in_channels,
ksize=ksize,
stride=stride,
groups=in_channels,
act=act,
)
self.pconv = BaseConv(
in_channels, out_channels, ksize=1, stride=1, groups=1, act=act
)
def forward(self, x):
x = self.dconv(x)
return self.pconv(x)
class Bottleneck(nn.Module):
# Standard bottleneck
def __init__(
self,
in_channels,
out_channels,
shortcut=True,
expansion=0.5,
depthwise=False,
act="silu",
):
super().__init__()
hidden_channels = int(out_channels * expansion)
Conv = DWConv if depthwise else BaseConv
self.conv1 = BaseConv(in_channels, hidden_channels, 1, stride=1, act=act)
self.conv2 = Conv(hidden_channels, out_channels, 3, stride=1, act=act)
self.use_add = shortcut and in_channels == out_channels
def forward(self, x):
y = self.conv2(self.conv1(x))
if self.use_add:
y = y + x
return y
class ResLayer(nn.Module):
"Residual layer with `in_channels` inputs."
def __init__(self, in_channels: int):
super().__init__()
mid_channels = in_channels // 2
self.layer1 = BaseConv(
in_channels, mid_channels, ksize=1, stride=1, act="lrelu"
)
self.layer2 = BaseConv(
mid_channels, in_channels, ksize=3, stride=1, act="lrelu"
)
def forward(self, x):
out = self.layer2(self.layer1(x))
return x + out
class SPPBottleneck(nn.Module):
"""Spatial pyramid pooling layer used in YOLOv3-SPP"""
def __init__(
self, in_channels, out_channels, kernel_sizes=(5, 9, 13), activation="silu"
):
super().__init__()
hidden_channels = in_channels // 2
self.conv1 = BaseConv(in_channels, hidden_channels, 1, stride=1, act=activation)
self.m = nn.ModuleList(
[
nn.MaxPool2d(kernel_size=ks, stride=1, padding=ks // 2)
for ks in kernel_sizes
]
)
conv2_channels = hidden_channels * (len(kernel_sizes) + 1)
self.conv2 = BaseConv(conv2_channels, out_channels, 1, stride=1, act=activation)
def forward(self, x):
x = self.conv1(x)
x = torch.cat([x] + [m(x) for m in self.m], dim=1)
x = self.conv2(x)
return x
class CSPLayer(nn.Module):
"""C3 in yolov5, CSP Bottleneck with 3 convolutions"""
def __init__(
self,
in_channels,
out_channels,
n=1,
shortcut=True,
expansion=0.5,
depthwise=False,
act="silu",
):
"""
Args:
in_channels (int): input channels.
out_channels (int): output channels.
n (int): number of Bottlenecks. Default value: 1.
"""
# ch_in, ch_out, number, shortcut, groups, expansion
super().__init__()
hidden_channels = int(out_channels * expansion) # hidden channels
self.conv1 = BaseConv(in_channels, hidden_channels, 1, stride=1, act=act)
self.conv2 = BaseConv(in_channels, hidden_channels, 1, stride=1, act=act)
self.conv3 = BaseConv(2 * hidden_channels, out_channels, 1, stride=1, act=act)
module_list = [
Bottleneck(
hidden_channels, hidden_channels, shortcut, 1.0, depthwise, act=act
)
for _ in range(n)
]
self.m = nn.Sequential(*module_list)
def forward(self, x):
x_1 = self.conv1(x)
x_2 = self.conv2(x)
x_1 = self.m(x_1)
x = torch.cat((x_1, x_2), dim=1)
return self.conv3(x)
class Focus(nn.Module):
"""Focus width and height information into channel space."""
def __init__(self, in_channels, out_channels, ksize=1, stride=1, act="silu"):
super().__init__()
self.conv = BaseConv(in_channels * 4, out_channels, ksize, stride, act=act)
def forward(self, x):
# shape of x (b,c,w,h) -> y(b,4c,w/2,h/2)
patch_top_left = x[..., ::2, ::2]
patch_top_right = x[..., ::2, 1::2]
patch_bot_left = x[..., 1::2, ::2]
patch_bot_right = x[..., 1::2, 1::2]
x = torch.cat(
(
patch_top_left,
patch_bot_left,
patch_top_right,
patch_bot_right,
),
dim=1,
)
return self.conv(x)
class LVCBlock(nn.Module):
def __init__(self, in_channels, out_channels, num_codes, channel_ratio=0.25, base_channel=64):
super(LVCBlock, self).__init__()
self.out_channels = out_channels
self.num_codes = num_codes
num_codes = 64
self.conv_1 = ConvBlock(in_channels=in_channels, out_channels=in_channels, res_conv=True, stride=1)
self.LVC = nn.Sequential(
nn.Conv2d(in_channels, in_channels, 1, bias=False),
nn.BatchNorm2d(in_channels),
nn.ReLU(inplace=True),
Encoding(in_channels=in_channels, num_codes=num_codes),
nn.BatchNorm1d(num_codes),
nn.ReLU(inplace=True),
Mean(dim=1))
self.fc = nn.Sequential(nn.Linear(in_channels, in_channels), nn.Sigmoid())
def forward(self, x):
x = self.conv_1(x, return_x_2=False)
en = self.LVC(x)
gam = self.fc(en)
b, in_channels, _, _ = x.size()
y = gam.view(b, in_channels, 1, 1)
x = F.relu_(x + x * y)
return x
# LightMLPBlock
class LightMLPBlock(nn.Module):
def __init__(self, in_channels, out_channels, ksize=1, stride=1, act="silu",
mlp_ratio=4., drop=0., act_layer=nn.GELU,
use_layer_scale=True, layer_scale_init_value=1e-5, drop_path=0., norm_layer=GroupNorm): # act_layer=nn.GELU,
super().__init__()
self.dw = DWConv(in_channels, out_channels, ksize=1, stride=1, act="silu")
self.linear = nn.Linear(out_channels, out_channels) # learnable position embedding
self.out_channels = out_channels
self.norm1 = norm_layer(in_channels)
self.norm2 = norm_layer(in_channels)
mlp_hidden_dim = int(in_channels * mlp_ratio)
self.mlp = Mlp(in_features=in_channels, hidden_features=mlp_hidden_dim, act_layer=nn.GELU,
drop=drop)
self.drop_path = DropPath(drop_path) if drop_path > 0. \
else nn.Identity()
self.use_layer_scale = use_layer_scale
if use_layer_scale:
self.layer_scale_1 = nn.Parameter(
layer_scale_init_value * torch.ones((out_channels)), requires_grad=True)
self.layer_scale_2 = nn.Parameter(
layer_scale_init_value * torch.ones((out_channels)), requires_grad=True)
def forward(self, x):
if self.use_layer_scale:
x = x + self.drop_path(self.layer_scale_1.unsqueeze(-1).unsqueeze(-1) * self.dw(self.norm1(x)))
x = x + self.drop_path(self.layer_scale_2.unsqueeze(-1).unsqueeze(-1) * self.mlp(self.norm2(x)))
else:
x = x + self.drop_path(self.dw(self.norm1(x)))
x = x + self.drop_path(self.mlp(self.norm2(x)))
return x
# EVCBlock
class EVCBlock(nn.Module):
def __init__(self, in_channels, out_channels, channel_ratio=4, base_channel=16):
super().__init__()
expansion = 2
ch = out_channels * expansion
# Stem stage: get the feature maps by conv block (copied form resnet.py) 进入conformer框架之前的处理
self.conv1 = nn.Conv2d(in_channels, in_channels, kernel_size=7, stride=1, padding=3, bias=False) # 1 / 2 [112, 112]
self.bn1 = nn.BatchNorm2d(in_channels)
self.act1 = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=1, padding=1) # 1 / 4 [56, 56]
# LVC
self.lvc = LVCBlock(in_channels=in_channels, out_channels=out_channels, num_codes=64) # c1值暂时未定
# LightMLPBlock
self.l_MLP = LightMLPBlock(in_channels, out_channels, ksize=1, stride=1, act="silu", act_layer=nn.GELU, mlp_ratio=4., drop=0.,
use_layer_scale=True, layer_scale_init_value=1e-5, drop_path=0., norm_layer=GroupNorm)
self.cnv1 = nn.Conv2d(ch, out_channels, kernel_size=1, stride=1, padding=0)
def forward(self, x):
x1 = self.maxpool(self.act1(self.bn1(self.conv1(x))))
# LVCBlock
x_lvc = self.lvc(x1)
# LightMLPBlock
x_lmlp = self.l_MLP(x1)
# concat
x = torch.cat((x_lvc, x_lmlp), dim=1)
x = self.cnv1(x)
return x
- 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
2.将ECVblock添加到backbone中
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 6, C3, [256]], # 4
[-1, 1, EVCBlock, [256, 256]], # update
[-2, 1, Conv, [512, 3, 2]], # 6-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 8-P5/32
[-1, 3, C3, [1024]],
[-1, 1, SPPF, [1024, 5]], # 10
]
# YOLOv5 v6.0 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 7], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 5], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 15], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 11], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[18, 21, 24], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
- 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
3.将将ECVblock添加到head中
# YOLOv5 v6.0 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[-1, 1, EVCBlock, [512, 512]], # update
[[-1, 6], 1, Concat, [1]], # cat backbone P4 -2 输出
[-1, 3, C3, [512, False]], # 13 ---
[-1, 1, Conv, [256, 1, 1]], #
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3 # 512
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 15], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[18, 21, 24], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/笔触狂放9/article/detail/334988
推荐阅读
相关标签
