1,本文介绍
ResNet(深度残差网络)通过引入“快捷连接”来解决深层神经网络训练中的梯度消失问题。这些快捷连接允许网络的输入直接跳过中间的层,直接传递到后面的层,从而使得网络能够专注于学习输入与输出之间的残差(即差异),而非直接学习复杂的函数映射。这种设计方式使得网络在需要时可以简单地实现恒等映射,简化了训练过程,缓解了深层网络训练中的困难。因此,ResNet 能够有效地训练非常深的网络结构,并在多个视觉识别任务上取得显著的性能提升。
关于ResNet的详细介绍可以看论文:https://arxiv.org/pdf/1512.03385.pdf
本文将讲解如何将ResNet融合进yolov8
话不多说,上代码!
2, 将ResNet融合进yolov8
2.1 步骤一
首先找到如下的目录'ultralytics/nn',然后在这个目录下创建一个'Addmodules'文件夹,然后在这个目录下创建一个ResNet.py文件,文件名字可以根据你自己的习惯起,然后将ResNet的核心代码复制进去。
from collections import OrderedDict
import torch.nn as nn
import torch.nn.functional as F
class ConvNormLayer(nn.Module):
def __init__(self,
ch_in,
ch_out,
filter_size,
stride,
groups=1,
act=None):
super(ConvNormLayer, self).__init__()
self.act = act
self.conv = nn.Conv2d(
in_channels=ch_in,
out_channels=ch_out,
kernel_size=filter_size,
stride=stride,
padding=(filter_size - 1) // 2,
groups=groups)
self.norm = nn.BatchNorm2d(ch_out)
def forward(self, inputs):
out = self.conv(inputs)
out = self.norm(out)
if self.act:
out = getattr(F, self.act)(out)
return out
class SELayer(nn.Module):
def __init__(self, ch, reduction_ratio=16):
super(SELayer, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.fc = nn.Sequential(
nn.Linear(ch, ch // reduction_ratio, bias=False),
nn.ReLU(inplace=True),
nn.Linear(ch // reduction_ratio, ch, bias=False),
nn.Sigmoid()
)
def forward(self, x):
b, c, _, _ = x.size()
y = self.avg_pool(x).view(b, c)
y = self.fc(y).view(b, c, 1, 1)
return x * y.expand_as(x)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self,
ch_in,
ch_out,
stride,
shortcut,
act='relu',
variant='b',
att=False):
super(BasicBlock, self).__init__()
self.shortcut = shortcut
if not shortcut:
if variant == 'd' and stride == 2:
self.short = nn.Sequential()
self.short.add_sublayer(
'pool',
nn.AvgPool2d(
kernel_size=2, stride=2, padding=0, ceil_mode=True))
self.short.add_sublayer(
'conv',
ConvNormLayer(
ch_in=ch_in,
ch_out=ch_out,
filter_size=1,
stride=1))
else:
self.short = ConvNormLayer(
ch_in=ch_in,
ch_out=ch_out,
filter_size=1,
stride=stride)
self.branch2a = ConvNormLayer(
ch_in=ch_in,
ch_out=ch_out,
filter_size=3,
stride=stride,
act='relu')
self.branch2b = ConvNormLayer(
ch_in=ch_out,
ch_out=ch_out,
filter_size=3,
stride=1,
act=None)
self.att = att
if self.att:
self.se = SELayer(ch_out)
def forward(self, inputs):
out = self.branch2a(inputs)
out = self.branch2b(out)
if self.att:
out = self.se(out)
if self.shortcut:
short = inputs
else:
short = self.short(inputs)
out = out + short
out = F.relu(out)
return out
class BottleNeck(nn.Module):
expansion = 4
def __init__(self, ch_in, ch_out, stride, shortcut, act='relu', variant='d', att=False):
super().__init__()
if variant == 'a':
stride1, stride2 = stride, 1
else:
stride1, stride2 = 1, stride
width = ch_out
self.branch2a = ConvNormLayer(ch_in, width, 1, stride1, act=act)
self.branch2b = ConvNormLayer(width, width, 3, stride2, act=act)
self.branch2c = ConvNormLayer(width, ch_out * self.expansion, 1, 1)
self.shortcut = shortcut
if not shortcut:
if variant == 'd' and stride == 2:
self.short = nn.Sequential(OrderedDict([
('pool', nn.AvgPool2d(2, 2, 0, ceil_mode=True)),
('conv', ConvNormLayer(ch_in, ch_out * self.expansion, 1, 1))
]))
else:
self.short = ConvNormLayer(ch_in, ch_out * self.expansion, 1, stride)
self.att = att
if self.att:
self.se = SELayer(ch_out)
def forward(self, x):
out = self.branch2a(x)
out = self.branch2b(out)
out = self.branch2c(out)
if self.att:
out = self.se(out)
if self.shortcut:
short = x
else:
short = self.short(x)
out = out + short
out = F.relu(out)
return out
class Blocks(nn.Module):
def __init__(self,
ch_in,
ch_out,
count,
block,
stage_num,
att=False,
variant='b'):
super(Blocks, self).__init__()
self.blocks = nn.ModuleList()
block = globals()[block]
for i in range(count):
self.blocks.append(
block(
ch_in,
ch_out,
stride=2 if i == 0 and stage_num != 2 else 1,
shortcut=False if i == 0 else True,
variant=variant,
att=att)
)
if i == 0:
ch_in = ch_out * block.expansion
def forward(self, inputs):
block_out = inputs
for block in self.blocks:
block_out = block(block_out)
return block_out
2.2 步骤二
在Addmodules下创建一个新的py文件名字为'init.py',然后在其内部添加如下代码
2.3 步骤三
在task.py进行导入
2.4 步骤四
在task.py进行注册,即在parse_model添加代码
注意-共需要在三个位置修改
然后如下图所示,注释掉黄色框内代码,添加红色框内代码
到此注册成功,复制后面的yaml文件直接运行即可
yaml文件1-ResNet18
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, ConvNormLayer, [32, 3, 2, 1, 'relu']] # 0-P1
- [-1, 1, ConvNormLayer, [32, 3, 1, 1, 'relu']] # 1
- [-1, 1, ConvNormLayer, [64, 3, 1, 1, 'relu']] # 2
- [-1, 1, nn.MaxPool2d, [3, 2, 1]] # 3-P2
- [-1, 2, Blocks, [64, BasicBlock, 2, False]] # 4
- [-1, 2, Blocks, [128, BasicBlock, 3, False]] # 5-P3
- [-1, 2, Blocks, [256, BasicBlock, 4, False]] # 6-P4
- [-1, 2, Blocks, [512, BasicBlock, 5, False]] # 7-P5
- [-1, 1, SPPF, [1024, 5]] # 8
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 11
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 5], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 14 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 17 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 8], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 20 (P5/32-large)
- [[14, 17, 20], 1, Detect, [nc]] # Detect(P3, P4, P5)
yaml文件2-ResNet34
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, ConvNormLayer, [32, 3, 2, 1, 'relu']] # 0-P1
- [-1, 1, ConvNormLayer, [32, 3, 1, 1, 'relu']] # 1
- [-1, 1, ConvNormLayer, [64, 3, 1, 1, 'relu']] # 2
- [-1, 1, nn.MaxPool2d, [3, 2, 1]] # 3-P2
- [-1, 3, Blocks, [64, BasicBlock, 2, False]] # 4
- [-1, 4, Blocks, [128, BasicBlock, 3, False]] # 5-P3
- [-1, 6, Blocks, [256, BasicBlock, 4, False]] # 6-P4
- [-1, 3, Blocks, [512, BasicBlock, 5, False]] # 7-P5
- [-1, 1, SPPF, [1024, 5]] # 8
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 11
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 5], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 14 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 17 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 8], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 20 (P5/32-large)
- [[14, 17, 20], 1, Detect, [nc]] # Detect(P3, P4, P5)
yaml文件3-ResNet50
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, ConvNormLayer, [32, 3, 2, 1, 'relu']] # 0-P1
- [-1, 1, ConvNormLayer, [32, 3, 1, 1, 'relu']] # 1
- [-1, 1, ConvNormLayer, [64, 3, 1, 1, 'relu']] # 2
- [-1, 1, nn.MaxPool2d, [3, 2, 1]] # 3-P2
- [-1, 3, Blocks, [64, BasicBlock, 2, False]] # 4
- [-1, 4, Blocks, [128, BasicBlock, 3, False]] # 5-P3
- [-1, 6, Blocks, [256, BasicBlock, 4, False]] # 6-P4
- [-1, 3, Blocks, [512, BasicBlock, 5, False]] # 7-P5
- [-1, 1, SPPF, [1024, 5]] # 8
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 11
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 5], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 14 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 17 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 8], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 20 (P5/32-large)
- [[14, 17, 20], 1, Detect, [nc]] # Detect(P3, P4, P5)
yaml文件4-ResNet101
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, ConvNormLayer, [32, 3, 2, 1, 'relu']] # 0-P1
- [-1, 1, ConvNormLayer, [32, 3, 1, 1, 'relu']] # 1
- [-1, 1, ConvNormLayer, [64, 3, 1, 1, 'relu']] # 2
- [-1, 1, nn.MaxPool2d, [3, 2, 1]] # 3-P2
- [-1, 3, Blocks, [64, BasicBlock, 2, False]] # 4
- [-1, 4, Blocks, [128, BasicBlock, 3, False]] # 5-P3
- [-1, 23, Blocks, [256, BasicBlock, 4, False]] # 6-P4
- [-1, 3, Blocks, [512, BasicBlock, 5, False]] # 7-P5
- [-1, 1, SPPF, [1024, 5]] # 8
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 11
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 5], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 14 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 17 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 8], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 20 (P5/32-large)
- [[14, 17, 20], 1, Detect, [nc]] # Detect(P3, P4, P5)
不知不觉已经看完了哦,动动小手留个点赞吧--_--
版权归原作者 不想敲代码!!! 所有, 如有侵权,请联系我们删除。