FPN网络结构及Pytorch实现

FPN总体架构如图所示，主要包含自下而上网络、自上而下网络、横向连接与卷积融合4个部分。

自下而上：C2到C5代表不同的ResNet卷积组，这些卷积组包含了多个Bottleneck结构，组内的特征图大小相同，组间大小递减。

自下而上：首先对C5进行1x1卷积降低通道数得到P5，然后依次进行上采样得到P4、P3、P2.目的是得到与C4、C3与C2长宽相同的特征，方便下次进行逐元素相加。采用2倍最近邻上采样（直接对临近元素进行复制，而非线性插值）。

横向连接：（Lateral Connection）目的是为了将上采样后的高语义特征与浅层的定位细节进行融合。高语义特征经过上采样后，其长宽与对应的浅层特征相同，而通道数固定为256。因此需要对特征C2——C4进行1x1卷积使得其通道数变为256.，然后两者进行逐元素相加得到P4、P3与P2。

卷积融合：在得到相加后的特征后，利用3x3卷积对生成的P2，P3，P4进行融合。目的是消除上采样过程中带来的重叠效应，以生成最终的特征图。


import torch.nn as nn
import torch.nn.functional as F
import math#ResNet的基本Bottleneck类
class Bottleneck(nn.Module):expansion=4#通道倍增数def __init__(self,in_planes,planes,stride=1,downsample=None):super(Bottleneck,self).__init__()self.bottleneck=nn.Sequential(nn.Conv2d(in_planes,planes,1,bias=False),nn.BatchNorm2d(planes),nn.ReLU(inplace=True),nn.Conv2d(planes,planes,3,stride,1,bias=False),nn.BatchNorm2d(planes),nn.ReLU(inplace=True),nn.Conv2d(planes,self.expansion*planes,1,bias=False),nn.BatchNorm2d(self.expansion*planes),)self.relu=nn.ReLU(inplace=True)self.downsample=downsampledef forward(self,x):identity=xout=self.bottleneck(x)if self.expansion is not None:identity=self.downsample(x)out+=identityout=self.relu(out)return out#FNP的类，初始化需要一个list，代表RESNET的每一个阶段的Bottleneck的数量
class FPN(nn.Module):def __init__(self,layers):super(FPN,self).__init__()self.inplanes=64#处理输入的C1模块（C1代表了RestNet的前几个卷积与池化层）self.conv1=nn.Conv2d(3,64,7,2,3,bias=False)self.bn1=nn.BatchNorm2d(64)self.relu=nn.ReLU(inplace=True)self.maxpool=nn.MaxPool2d(3,2,1)#搭建自下而上的C2，C3，C4，C5self.layer1=self._make_layer(64,layers[0])self.layer2=self._make_layer(128,layers[1],2)self.layer3=self._make_layer(256,layers[2],2)self.layer4=self._make_layer(512,layers[3],2)#对C5减少通道数，得到P5self.toplayer=nn.Conv2d(2048,256,1,1,0)#3x3卷积融合特征self.smooth1=nn.Conv2d(256,256,3,1,1)self.smooth2=nn.Conv2d(256,256,3,1,1)self.smooth3=nn.Conv2d(256,256,3,1,1)#横向连接，保证通道数相同self.latlayer1=nn.Conv2d(1024,256,1,1,0)self.latlayer2=nn.Conv2d(512,256,1,1,0)self.latlayer3=nn.Conv2d(256,256,1,1,0)def _make_layer(self,planes,blocks,stride=1):downsample=Noneif stride!=1 or self.inplanes != Bottleneck.expansion*planes:downsample=nn.Sequential(nn.Conv2d(self.inplanes,Bottleneck.expansion*planes,1,stride,bias=False),nn.BatchNorm2d(Bottleneck.expansion*planes))layers=[]layers.append(Bottleneck(self.inplanes,planes,stride,downsample))self.inplanes=planes*Bottleneck.expansionfor i in range(1,blocks):layers.append(Bottleneck(self.inplanes,planes))return nn.Sequential(*layers)#自上而下的采样模块def _upsample_add(self,x,y):_,_,H,W=y.shapereturn F.upsample(x,size=(H,W),mode='bilinear')+ydef forward(self,x):#自下而上c1=self.maxpool(self.relu(self.bn1(self.conv1(x))))c2=self.layer1(c1)c3=self.layer2(c2)c4=self.layer3(c3)c5=self.layer4(c4)#自上而下p5=self.toplayer(c5)p4=self._upsample_add(p5,self.latlayer1(c4))p3=self._upsample_add(p4,self.latlayer2(c3))p2=self._upsample_add(p3,self.latlayer3(c2))#卷积的融合，平滑处理p4=self.smooth1(p4)p3=self.smooth2(p3)p2=self.smooth3(p2)return p2,p3,p4,p5

net=FPN([3,4,6,3])
net

FPN((conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)(maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)(layer1): Sequential((0): Bottleneck((bottleneck): Sequential((0): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True)(downsample): Sequential((0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(1): Bottleneck((bottleneck): Sequential((0): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True))(2): Bottleneck((bottleneck): Sequential((0): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True)))(layer2): Sequential((0): Bottleneck((bottleneck): Sequential((0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True)(downsample): Sequential((0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(1): Bottleneck((bottleneck): Sequential((0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True))(2): Bottleneck((bottleneck): Sequential((0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True))(3): Bottleneck((bottleneck): Sequential((0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True)))(layer3): Sequential((0): Bottleneck((bottleneck): Sequential((0): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True)(downsample): Sequential((0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(1): Bottleneck((bottleneck): Sequential((0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True))(2): Bottleneck((bottleneck): Sequential((0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True))(3): Bottleneck((bottleneck): Sequential((0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True))(4): Bottleneck((bottleneck): Sequential((0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True))(5): Bottleneck((bottleneck): Sequential((0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True)))(layer4): Sequential((0): Bottleneck((bottleneck): Sequential((0): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)(4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True)(downsample): Sequential((0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)(1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(1): Bottleneck((bottleneck): Sequential((0): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True))(2): Bottleneck((bottleneck): Sequential((0): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(2): ReLU(inplace=True)(3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(5): ReLU(inplace=True)(6): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)(7): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True))(relu): ReLU(inplace=True)))(toplayer): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1))(smooth1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(smooth2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(smooth3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(latlayer1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))(latlayer2): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))(latlayer3): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
)

FPN网络结构及Pytorch实现相关推荐

resnet，retinanet,fpn网络结构及pytorch实现代码
关于resnet,其巧妙地利用了shortcut连接,解决了深度网络中模型退化的问题.网络结构如下 FPN的目的熟悉faster rcnn的人都知道,faster rcnn利用的是vgg的最后卷积特 ...
fpn网络结构及代码
文章目录一.fpn网络结构二.代码一.fpn网络结构 resnet结构组成. fpn(Feature Pyramid Networks)架构如上图所示,以resnet50作为backbone.通 ...
机器学习之神经网络（从神经网络结构到pytorch基本用法）
机器学习之神经网络(从神经网络结构到pytorch基本用法) 1.神经网络概念 1.1 网络结构人工神经网络(artificial neural network,ANN),简称神经网络(neur ...
ResNet50 网络结构搭建(PyTorch)
ResNet50是一个经典的特征提取网络结构,虽然Pytorch已有官方实现,但为了加深对网络结构的理解,还是自己动手敲敲代码搭建一下.需要特别说明的是,笔者是以熟悉网络各层输出维度变化为目的的,只对 ...
【深度学习】VGG16网络结构复现 | pytorch |
文章目录前言一.VGG16介绍二.VGG16网络复现--pytorch 前言这篇文章按道理来说应该是很简单的,但是因为一个很小的bug,让我难受了一晚上,直到现在我也没找出原因.后面我会提到这 ...
SSD网络以及FSSD网络结构基于pytorch的搭建
SSD网络,具体可阅读SSD相关论文: SSD网络:#-*-coding:utf-8-*- import torch import torch.nn as nn import torch.nn.fun ...
9 大主题卷积神经网络（CNN）的 PyTorch 实现
Datawhale干货作者:红色石头,北京大学,Datawhale伙伴大家还记得这张图吗? 之前,红色石头发文介绍过一份很不错的资源: 52 个深度学习目标检测模型汇总,论文.源码一应俱全! 深度 ...
【深度学习】9 大主题卷积神经网络（CNN）的 PyTorch 实现
大家还记得这张图吗? 之前,红色石头发文介绍过一份很不错的资源: 52 个深度学习目标检测模型汇总,论文.源码一应俱全! 深度系统介绍了 52 个目标检测模型,纵观 2013 年到 2020 年,从最 ...
目标检测算法之FPN（附FPN代码实现）
论文题目:FeaturePyramidNetworksforObjectDetection 论文链接:https://arxiv.org/abs/1612.03144 所要解决的问题针对小目标检测网 ...
pytorch模型加载测试_使用Pytorch实现物体检测（Faster R-CNN）
在本示例中,介绍一种two-stage算法(Faster R-CNN),将目标区域检测和类别识别分为两个任务进行物体检测.本示例采用PyTorch引擎进行模型构建. 如果您已熟练使用Notebook和 ...

FPN网络结构及Pytorch实现

FPN网络结构及Pytorch实现相关推荐

最新文章

热门文章