DAMO-YOLO的Neck( Efficient RepGFPN)详解

2023-11-29 05:30

本文主要是介绍DAMO-YOLO的Neck( Efficient RepGFPN)详解,希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!

 这个图是有点问题的,在GiraffeNeckV2代码中只有了5个Fusion Block(图中有6个)

https://github.com/tinyvision/DAMO-YOLO/blob/master/damo/base_models/necks/giraffe_fpn_btn.py

代码中只有5个CSPStage

所以我自己画了一个总体图,在github上提了个issue,得到了原作者的肯定

I think the pictures in your paper are not rigorous in several places · Issue #91 · tinyvision/DAMO-YOLO · GitHub

 

想要看懂Neck部分,只需要看懂Fusion Block在做什么就行了,其他部分和PAN差不太多

class CSPStage(nn.Module):   def __init__(self,block_fn,ch_in,ch_hidden_ratio,ch_out,n,act='swish',spp=False):super(CSPStage, self).__init__()split_ratio = 2ch_first = int(ch_out // split_ratio)ch_mid = int(ch_out - ch_first)self.conv1 = ConvBNAct(ch_in, ch_first, 1, act=act)self.conv2 = ConvBNAct(ch_in, ch_mid, 1, act=act)self.convs = nn.Sequential()next_ch_in = ch_midfor i in range(n):if block_fn == 'BasicBlock_3x3_Reverse':self.convs.add_module(str(i),BasicBlock_3x3_Reverse(next_ch_in,ch_hidden_ratio,ch_mid,act=act,shortcut=True))else:raise NotImplementedErrorif i == (n - 1) // 2 and spp:self.convs.add_module('spp', SPP(ch_mid * 4, ch_mid, 1, [5, 9, 13], act=act))next_ch_in = ch_midself.conv3 = ConvBNAct(ch_mid * n + ch_first, ch_out, 1, act=act)def forward(self, x):y1 = self.conv1(x)y2 = self.conv2(x)mid_out = [y1]for conv in self.convs:y2 = conv(y2)mid_out.append(y2)y = torch.cat(mid_out, axis=1)y = self.conv3(y)return y

以上是CSPStage的代码,要想看懂,我们得先看懂ConvBNAct、BasicBlock_3x3_Reverse这两个类

class ConvBNAct(nn.Module):"""A Conv2d -> Batchnorm -> silu/leaky relu block"""def __init__(self,in_channels,out_channels,ksize,stride=1,groups=1,bias=False,act='silu',norm='bn',reparam=False,):super().__init__()# same paddingpad = (ksize - 1) // 2self.conv = nn.Conv2d(in_channels,out_channels,kernel_size=ksize,stride=stride,padding=pad,groups=groups,bias=bias,)if norm is not None:self.bn = get_norm(norm, out_channels, inplace=True)if act is not None:self.act = get_activation(act, inplace=True)self.with_norm = norm is not Noneself.with_act = act is not Nonedef forward(self, x):x = self.conv(x)if self.with_norm:x = self.bn(x)if self.with_act:x = self.act(x)return xdef fuseforward(self, x):return self.act(self.conv(x))

ConvBNAct还是很好看懂的,Conv +BN + SiLU就完事了(也可用别的激活函数,文章用SiLU)

 如果设置了groups参数就变成了组卷积了

class BasicBlock_3x3_Reverse(nn.Module):def __init__(self,ch_in,ch_hidden_ratio,ch_out,act='relu',shortcut=True):super(BasicBlock_3x3_Reverse, self).__init__()assert ch_in == ch_outch_hidden = int(ch_in * ch_hidden_ratio)self.conv1 = ConvBNAct(ch_hidden, ch_out, 3, stride=1, act=act)self.conv2 = RepConv(ch_in, ch_hidden, 3, stride=1, act=act)self.shortcut = shortcutdef forward(self, x):y = self.conv2(x)y = self.conv1(y)if self.shortcut:return x + yelse:return y

要看懂BasicBlock_3x3_Reverse这个类,就得了解RepConv类,这个类就是根据RepVGG网络的RepVGGBlock改的

class RepConv(nn.Module):'''RepConv is a basic rep-style block, including training and deploy statusCode is based on https://github.com/DingXiaoH/RepVGG/blob/main/repvgg.py'''def __init__(self,in_channels,out_channels,kernel_size=3,stride=1,padding=1,dilation=1,groups=1,padding_mode='zeros',deploy=False,act='relu',norm=None):super(RepConv, self).__init__()self.deploy = deployself.groups = groupsself.in_channels = in_channelsself.out_channels = out_channelsassert kernel_size == 3assert padding == 1padding_11 = padding - kernel_size // 2if isinstance(act, str):self.nonlinearity = get_activation(act)else:self.nonlinearity = actif deploy:self.rbr_reparam = nn.Conv2d(in_channels=in_channels,out_channels=out_channels,kernel_size=kernel_size,stride=stride,padding=padding,dilation=dilation,groups=groups,bias=True,padding_mode=padding_mode)else:self.rbr_identity = Noneself.rbr_dense = conv_bn(in_channels=in_channels,out_channels=out_channels,kernel_size=kernel_size,stride=stride,padding=padding,groups=groups)self.rbr_1x1 = conv_bn(in_channels=in_channels,out_channels=out_channels,kernel_size=1,stride=stride,padding=padding_11,groups=groups)def forward(self, inputs):'''Forward process'''if hasattr(self, 'rbr_reparam'):return self.nonlinearity(self.rbr_reparam(inputs))if self.rbr_identity is None:id_out = 0else:id_out = self.rbr_identity(inputs)return self.nonlinearity(self.rbr_dense(inputs) + self.rbr_1x1(inputs) + id_out)def get_equivalent_kernel_bias(self):kernel3x3, bias3x3 = self._fuse_bn_tensor(self.rbr_dense)kernel1x1, bias1x1 = self._fuse_bn_tensor(self.rbr_1x1)kernelid, biasid = self._fuse_bn_tensor(self.rbr_identity)return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasiddef _pad_1x1_to_3x3_tensor(self, kernel1x1):if kernel1x1 is None:return 0else:return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1])def _fuse_bn_tensor(self, branch):if branch is None:return 0, 0if isinstance(branch, nn.Sequential):kernel = branch.conv.weightrunning_mean = branch.bn.running_meanrunning_var = branch.bn.running_vargamma = branch.bn.weightbeta = branch.bn.biaseps = branch.bn.epselse:assert isinstance(branch, nn.BatchNorm2d)if not hasattr(self, 'id_tensor'):input_dim = self.in_channels // self.groupskernel_value = np.zeros((self.in_channels, input_dim, 3, 3),dtype=np.float32)for i in range(self.in_channels):kernel_value[i, i % input_dim, 1, 1] = 1self.id_tensor = torch.from_numpy(kernel_value).to(branch.weight.device)kernel = self.id_tensorrunning_mean = branch.running_meanrunning_var = branch.running_vargamma = branch.weightbeta = branch.biaseps = branch.epsstd = (running_var + eps).sqrt()t = (gamma / std).reshape(-1, 1, 1, 1)return kernel * t, beta - running_mean * gamma / stddef switch_to_deploy(self):if hasattr(self, 'rbr_reparam'):returnkernel, bias = self.get_equivalent_kernel_bias()self.rbr_reparam = nn.Conv2d(in_channels=self.rbr_dense.conv.in_channels,out_channels=self.rbr_dense.conv.out_channels,kernel_size=self.rbr_dense.conv.kernel_size,stride=self.rbr_dense.conv.stride,padding=self.rbr_dense.conv.padding,dilation=self.rbr_dense.conv.dilation,groups=self.rbr_dense.conv.groups,bias=True)self.rbr_reparam.weight.data = kernelself.rbr_reparam.bias.data = biasfor para in self.parameters():para.detach_()self.__delattr__('rbr_dense')self.__delattr__('rbr_1x1')if hasattr(self, 'rbr_identity'):self.__delattr__('rbr_identity')if hasattr(self, 'id_tensor'):self.__delattr__('id_tensor')self.deploy = True

 RepConv的特点是结构重参数化,训练时采用三条分支,推理时将三个分支融合在一起,大大减少了推理时间(建议看看RepVGG的讲解视频),我图画得太丑了

  RepConv采用的两分支的结构(a)

 其他细节有缘再更,代码不难,慢慢看完全能懂。有写的不对的地方请见谅

这篇关于DAMO-YOLO的Neck( Efficient RepGFPN)详解的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!



http://www.chinasem.cn/article/431638

相关文章

Java Stream流使用案例深入详解

《JavaStream流使用案例深入详解》:本文主要介绍JavaStream流使用案例详解,本文通过实例代码给大家介绍的非常详细,对大家的学习或工作具有一定的参考借鉴价值,需要的朋友参考下吧... 目录前言1. Lambda1.1 语法1.2 没参数只有一条语句或者多条语句1.3 一个参数只有一条语句或者多

SpringBoot整合mybatisPlus实现批量插入并获取ID详解

《SpringBoot整合mybatisPlus实现批量插入并获取ID详解》这篇文章主要为大家详细介绍了SpringBoot如何整合mybatisPlus实现批量插入并获取ID,文中的示例代码讲解详细... 目录【1】saveBATch(一万条数据总耗时:2478ms)【2】集合方式foreach(一万条数

Python装饰器之类装饰器详解

《Python装饰器之类装饰器详解》本文将详细介绍Python中类装饰器的概念、使用方法以及应用场景,并通过一个综合详细的例子展示如何使用类装饰器,希望对大家有所帮助,如有错误或未考虑完全的地方,望不... 目录1. 引言2. 装饰器的基本概念2.1. 函数装饰器复习2.2 类装饰器的定义和使用3. 类装饰

MySQL 中的 JSON 查询案例详解

《MySQL中的JSON查询案例详解》:本文主要介绍MySQL的JSON查询的相关知识,本文给大家介绍的非常详细,对大家的学习或工作具有一定的参考借鉴价值,需要的朋友参考下吧... 目录mysql 的 jsON 路径格式基本结构路径组件详解特殊语法元素实际示例简单路径复杂路径简写操作符注意MySQL 的 J

Python ZIP文件操作技巧详解

《PythonZIP文件操作技巧详解》在数据处理和系统开发中,ZIP文件操作是开发者必须掌握的核心技能,Python标准库提供的zipfile模块以简洁的API和跨平台特性,成为处理ZIP文件的首选... 目录一、ZIP文件操作基础三板斧1.1 创建压缩包1.2 解压操作1.3 文件遍历与信息获取二、进阶技

一文详解Java异常处理你都了解哪些知识

《一文详解Java异常处理你都了解哪些知识》:本文主要介绍Java异常处理的相关资料,包括异常的分类、捕获和处理异常的语法、常见的异常类型以及自定义异常的实现,文中通过代码介绍的非常详细,需要的朋... 目录前言一、什么是异常二、异常的分类2.1 受检异常2.2 非受检异常三、异常处理的语法3.1 try-

Java中的@SneakyThrows注解用法详解

《Java中的@SneakyThrows注解用法详解》:本文主要介绍Java中的@SneakyThrows注解用法的相关资料,Lombok的@SneakyThrows注解简化了Java方法中的异常... 目录前言一、@SneakyThrows 简介1.1 什么是 Lombok?二、@SneakyThrows

Java中字符串转时间与时间转字符串的操作详解

《Java中字符串转时间与时间转字符串的操作详解》Java的java.time包提供了强大的日期和时间处理功能,通过DateTimeFormatter可以轻松地在日期时间对象和字符串之间进行转换,下面... 目录一、字符串转时间(一)使用预定义格式(二)自定义格式二、时间转字符串(一)使用预定义格式(二)自

Redis Pipeline(管道) 详解

《RedisPipeline(管道)详解》Pipeline管道是Redis提供的一种批量执行命令的机制,通过将多个命令一次性发送到服务器并统一接收响应,减少网络往返次数(RTT),显著提升执行效率... 目录Redis Pipeline 详解1. Pipeline 的核心概念2. 工作原理与性能提升3. 核

Python正则表达式语法及re模块中的常用函数详解

《Python正则表达式语法及re模块中的常用函数详解》这篇文章主要给大家介绍了关于Python正则表达式语法及re模块中常用函数的相关资料,正则表达式是一种强大的字符串处理工具,可以用于匹配、切分、... 目录概念、作用和步骤语法re模块中的常用函数总结 概念、作用和步骤概念: 本身也是一个字符串,其中