● 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
● 🍦 参考文章:Pytorch实战 | 第P9周:YOLOv5-Backbone模块实现(训练营内部成员可读)
● 🍖 原作者:K同学啊|接辅导、项目定制
说明:
1.本次进学习YOLOv5-Backbone模块实现,其余程序与P8周相同
2.C3模块大致已经在上周了解,本次主要了解一下SPP结构
学习记录
1.CBS
CBS由一个二维卷积层+一个Bn层+一个SiLU激活函数构成
SiLU(x)=x⋅Sigmoid(x)
2.C3运作流程
输入A分为两个部分,第一部分通过一个卷积层得到输出A。
第二部分则通过一个CBS层+一个瓶颈层
瓶颈层中采用了shortcut
shortcut为了解决深度网络的梯度发散问题
输入B与经过两次卷积的输出B进行add操作得到输出C
最后输出C和经过卷积层的输出A通过concat操作拼接
3.SPPF
SPPF是SPP结构的改进,速度更快
运作流程为:
1.通过CBS层,即卷积层+BN层+SiLU,输出为x
2.x通过第一次最大池化记为y1,y1通过第二次最大池化层记为y2,最后通过一个最大池化层记为y3
3.将x,y1,y2,y3进行融合
4通过一个CBS层得到最终输出
看起来是可以获得不同层次(池化次数)的特征,融合局部特征和整体特征的效果
4.YOLOv5-Backbone模块组合方法
输入经过两个CBS层后,经过三组C3+CBS的组合,最后通过SPPF完成卷积操作
图的绘制者@K同学啊
YOLOv5-Backbone模块实现
import torch.nn.functional as F
def autopad(k, p=None): # kernel, padding
# Pad to 'same'
if p is None:
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
return p
class Conv(nn.Module):
# Standard convolution
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
super().__init__()
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
self.bn = nn.BatchNorm2d(c2)
self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
def forward(self, x):
return self.act(self.bn(self.conv(x)))
class Bottleneck(nn.Module):
# Standard bottleneck
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c_, c2, 3, 1, g=g)
self.add = shortcut and c1 == c2
def forward(self, x):
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
class C3(nn.Module):
# CSP Bottleneck with 3 convolutions
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c1, c_, 1, 1)
self.cv3 = Conv(2 * c_, c2, 1) # act=FReLU(c2)
self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
def forward(self, x):
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
class SPPF(nn.Module):
# Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
def __init__(self, c1, c2, k=5): # equivalent to SPP(k=(5, 9, 13))
super().__init__()
c_ = c1 // 2 # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c_ * 4, c2, 1, 1)
self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
def forward(self, x):
x = self.cv1(x)
with warnings.catch_warnings():
warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning
y1 = self.m(x)
y2 = self.m(y1)
return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
"""
这个是YOLOv5, 6.0版本的主干网络,这里进行复现
(注:有部分删改,详细讲解将在后续进行展开)
"""
class YOLOv5_backbone(nn.Module):
def __init__(self):
super(YOLOv5_backbone, self).__init__()
self.Conv_1 = Conv(3, 64, 3, 2, 2)
self.Conv_2 = Conv(64, 128, 3, 2)
self.C3_3 = C3(128,128)