SPP、SPPF 、 SimSPPF 、 ASPP、 SPPCSPC详解

分享自:https://blog.csdn.net/weixin_43694096/article/details/126354660

1. 原理

1.1 SPP(Spatial Pyramid Pooling)

SPP 模块是何凯大神在2015年的论文《Spatial Pyramid Pooling in Deep Convolution Networks for Visual Recognition》中提出来的.

SPP全称为空间金字塔池化结构,主要是为了解决两个问题

    1. 有效避免了对图像区域的裁剪、缩放操作导致的图像失真等问题。
    1. 解决了卷积神经网络对图相关重复特征提取的问题,大大提高了产生候选框的速度,且节省了计算成本

python 复制代码
class SPP(nn.Module):
    # Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
    def __init__(self, c1, c2, k=(5, 9, 13)):
        super().__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])

    def forward(self, x):
        x = self.cv1(x)
        with warnings.catch_warnings():
            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
            return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))

1.2 SPPF (Spatial Pyramid Pooling - Fast)

这个是Yolov5作者基于SPP提出的,速度较SPP快很多(2.5倍),所以叫做SPP-Fast

python 复制代码
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))

1.3 SimSPPF(Simplified SPPF)

美团YOLOv6提出的模块,感觉和SPPF只差了一个激活函数,简单测试了一下,单个ConvBNReLU速度比ConvBNSiLU18%

python 复制代码
class SimConv(nn.Module):
    '''Normal Conv with ReLU activation'''
    def __init__(self, in_channels, out_channels, kernel_size, stride, groups=1, bias=False):
        super().__init__()
        padding = kernel_size // 2
        self.conv = nn.Conv2d(
            in_channels,
            out_channels,
            kernel_size=kernel_size,
            stride=stride,
            padding=padding,
            groups=groups,
            bias=bias,
        )
        self.bn = nn.BatchNorm2d(out_channels)
        self.act = nn.ReLU()

    def forward(self, x):
        return self.act(self.bn(self.conv(x)))

    def forward_fuse(self, x):
        return self.act(self.conv(x))

class SimSPPF(nn.Module):
    '''Simplified SPPF with ReLU activation'''
    def __init__(self, in_channels, out_channels, kernel_size=5):
        super().__init__()
        c_ = in_channels // 2  # hidden channels
        self.cv1 = SimConv(in_channels, c_, 1, 1)
        self.cv2 = SimConv(c_ * 4, out_channels, 1, 1)
        self.m = nn.MaxPool2d(kernel_size=kernel_size, stride=1, padding=kernel_size // 2)

    def forward(self, x):
        x = self.cv1(x)
        with warnings.catch_warnings():
            warnings.simplefilter('ignore')
            y1 = self.m(x)
            y2 = self.m(y1)
            return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))

1.4 ASPP (Atrous Spatial Pyramid Pooling)

受到SPP的启发,语义分割模型DeepLabv2中提出了ASPP模块(空洞空间金字塔池化),该模块使用具有不同采样率的多个并行空洞卷积·。为每个采样率提取的特征在单独的分支中进一步处理,并融合以生成最终的结果。该模块通过不同的空洞率构建不同的感受野的卷积核,用来获取多尺度物体信息,具体结构比较简单如下图所示:

ASPP 是在DeepLab中提出来的,在后续的DeepLab版本中对其做了改进,如加入BN层,加入深度可分离卷积等,但基本的思路还是没变。

python 复制代码
# without BN version
class ASPP(nn.Module):
    def __init__(self, in_channel=512, out_channel=256):
        super(ASPP, self).__init__()
        self.mean = nn.AdaptiveAvgPool2d((1, 1))  # (1,1)means ouput_dim
        self.conv = nn.Conv2d(in_channel,out_channel, 1, 1)
        self.atrous_block1 = nn.Conv2d(in_channel, out_channel, 1, 1)
        self.atrous_block6 = nn.Conv2d(in_channel, out_channel, 3, 1, padding=6, dilation=6)
        self.atrous_block12 = nn.Conv2d(in_channel, out_channel, 3, 1, padding=12, dilation=12)
        self.atrous_block18 = nn.Conv2d(in_channel, out_channel, 3, 1, padding=18, dilation=18)
        self.conv_1x1_output = nn.Conv2d(out_channel * 5, out_channel, 1, 1)

    def forward(self, x):
        size = x.shape[2:]

        image_features = self.mean(x)
        image_features = self.conv(image_features)
        image_features = F.upsample(image_features, size=size, mode='bilinear')

        atrous_block1 = self.atrous_block1(x)
        atrous_block6 = self.atrous_block6(x)
        atrous_block12 = self.atrous_block12(x)
        atrous_block18 = self.atrous_block18(x)

        net = self.conv_1x1_output(torch.cat([image_features, atrous_block1, atrous_block6,
                                              atrous_block12, atrous_block18], dim=1))
        return net

1.5 RFB(Receptive Field Block)

RFB模块是在《ECCV2018:Receptive Field Block Net for Accurate and Fast Object Detection》一文中提出的,该文的出发点是模拟人类视觉的感受野从而加强网络的特征提取能力,在结构RFV借鉴了Inception的思想,主要是在Inception的基础上加入了空洞卷积,从而有效增大了感受野。



RFBRFB-s的架构,RFB-s用于浅层人类视网膜主题图中模拟较小的pRF,使用具有较小内核的更多分支。

python 复制代码
class BasicConv(nn.Module):

    def __init__(self, in_planes, out_planes, kernel_size, stride=1, padding=0, dilation=1, groups=1, relu=True, bn=True):
        super(BasicConv, self).__init__()
        self.out_channels = out_planes
        if bn:
            self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, groups=groups, bias=False)
            self.bn = nn.BatchNorm2d(out_planes, eps=1e-5, momentum=0.01, affine=True)
            self.relu = nn.ReLU(inplace=True) if relu else None
        else:
            self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, groups=groups, bias=True)
            self.bn = None
            self.relu = nn.ReLU(inplace=True) if relu else None

    def forward(self, x):
        x = self.conv(x)
        if self.bn is not None:
            x = self.bn(x)
        if self.relu is not None:
            x = self.relu(x)
        return x


class BasicRFB(nn.Module):

    def __init__(self, in_planes, out_planes, stride=1, scale=0.1, map_reduce=8, vision=1, groups=1):
        super(BasicRFB, self).__init__()
        self.scale = scale
        self.out_channels = out_planes
        inter_planes = in_planes // map_reduce

        self.branch0 = nn.Sequential(
            BasicConv(in_planes, inter_planes, kernel_size=1, stride=1, groups=groups, relu=False),
            BasicConv(inter_planes, 2 * inter_planes, kernel_size=(3, 3), stride=stride, padding=(1, 1), groups=groups),
            BasicConv(2 * inter_planes, 2 * inter_planes, kernel_size=3, stride=1, padding=vision + 1, dilation=vision, relu=False, groups=groups)
        )
        self.branch1 = nn.Sequential(
            BasicConv(in_planes, inter_planes, kernel_size=1, stride=1, groups=groups, relu=False),
            BasicConv(inter_planes, 2 * inter_planes, kernel_size=(3, 3), stride=stride, padding=(1, 1), groups=groups),
            BasicConv(2 * inter_planes, 2 * inter_planes, kernel_size=3, stride=1, padding=vision + 2, dilation=vision + 2, relu=False, groups=groups)
        )
        self.branch2 = nn.Sequential(
            BasicConv(in_planes, inter_planes, kernel_size=1, stride=1, groups=groups, relu=False),
            BasicConv(inter_planes, (inter_planes // 2) * 3, kernel_size=3, stride=1, padding=1, groups=groups),
            BasicConv((inter_planes // 2) * 3, 2 * inter_planes, kernel_size=3, stride=stride, padding=1, groups=groups),
            BasicConv(2 * inter_planes, 2 * inter_planes, kernel_size=3, stride=1, padding=vision + 4, dilation=vision + 4, relu=False, groups=groups)
        )

        self.ConvLinear = BasicConv(6 * inter_planes, out_planes, kernel_size=1, stride=1, relu=False)
        self.shortcut = BasicConv(in_planes, out_planes, kernel_size=1, stride=stride, relu=False)
        self.relu = nn.ReLU(inplace=False)

    def forward(self, x):
        x0 = self.branch0(x)
        x1 = self.branch1(x)
        x2 = self.branch2(x)

        out = torch.cat((x0, x1, x2), 1)
        out = self.ConvLinear(out)
        short = self.shortcut(x)
        out = out * self.scale + short
        out = self.relu(out)

        return out

1.6 SPPCSPC

该模块是YOLOv7中使用的SPP结构,表现优于SPPF,但参数量和计算量提升了很多。

python 复制代码
class SPPCSPC(nn.Module):
    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=(5, 9, 13)):
        super(SPPCSPC, self).__init__()
        c_ = int(2 * c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(c_, c_, 3, 1)
        self.cv4 = Conv(c_, c_, 1, 1)
        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
        self.cv5 = Conv(4 * c_, c_, 1, 1)
        self.cv6 = Conv(c_, c_, 3, 1)
        self.cv7 = Conv(2 * c_, c2, 1, 1)

    def forward(self, x):
        x1 = self.cv4(self.cv3(self.cv1(x)))
        y1 = self.cv6(self.cv5(torch.cat([x1] + [m(x1) for m in self.m], 1)))
        y2 = self.cv2(x)
        return self.cv7(torch.cat((y1, y2), dim=1))
python 复制代码
#分组SPPCSPC 分组后参数量和计算量与原本差距不大,不知道效果怎么样
class SPPCSPC_group(nn.Module):
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=(5, 9, 13)):
        super(SPPCSPC_group, self).__init__()
        c_ = int(2 * c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1, g=4)
        self.cv2 = Conv(c1, c_, 1, 1, g=4)
        self.cv3 = Conv(c_, c_, 3, 1, g=4)
        self.cv4 = Conv(c_, c_, 1, 1, g=4)
        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
        self.cv5 = Conv(4 * c_, c_, 1, 1, g=4)
        self.cv6 = Conv(c_, c_, 3, 1, g=4)
        self.cv7 = Conv(2 * c_, c2, 1, 1, g=4)

    def forward(self, x):
        x1 = self.cv4(self.cv3(self.cv1(x)))
        y1 = self.cv6(self.cv5(torch.cat([x1] + [m(x1) for m in self.m], 1)))
        y2 = self.cv2(x)
        return self.cv7(torch.cat((y1, y2), dim=1))

1.7 SPPFCSPC

借鉴了SPPF的思想将SPPCSPC优化了一下,得到了SPPFCSPC,在保持感受野不变的情况下获得速度提升;

目前这个结构被YOLOv6 3.0版本使用了,效果很不错,大家可以看YOLOv6 3.0的论文,里面有详细的实验结果。

python 复制代码
class SPPFCSPC(nn.Module):
    
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=5):
        super(SPPFCSPC, self).__init__()
        c_ = int(2 * c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(c_, c_, 3, 1)
        self.cv4 = Conv(c_, c_, 1, 1)
        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
        self.cv5 = Conv(4 * c_, c_, 1, 1)
        self.cv6 = Conv(c_, c_, 3, 1)
        self.cv7 = Conv(2 * c_, c2, 1, 1)

    def forward(self, x):
        x1 = self.cv4(self.cv3(self.cv1(x)))
        x2 = self.m(x1)
        x3 = self.m(x2)
        y1 = self.cv6(self.cv5(torch.cat((x1,x2,x3, self.m(x3)),1)))
        y2 = self.cv2(x)
        return self.cv7(torch.cat((y1, y2), dim=1))

2. 参数量对比

这里以yolov5s.yaml中使用各个模型替换SPP模块

3. 改进方式

  • (1) : 各个代码放入common.py
  • (2): yolo.py中加入类名
  • (3): 修改配置文件

yolov5配置文件如下:

shell 复制代码
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license

# 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]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
   # [-1, 1, ASPP, [512]],  # 9
   # [-1, 1, SPP, [1024]],
   # [-1, 1, SimSPPF, [1024, 5]],
   # [-1, 1, BasicRFB, [1024]],
   # [-1, 1, SPPCSPC, [1024]],
   # [-1, 1, SPPFCSPC, [1024, 5]], # 🍀
  ]

4 Issue

Q Why use SPPCPC instead of SPPFCSPC

yolov5's SPPF is much faster than SPP

why not try to replace SPPCSPC with SPPFCSPC:

A: Max pooling uses very few compution,if you programing well, above one could run three max pool layers in parallel, while below one must process thress max pool layers sequentially

By the way,you could replace SPPCSPC by SPPFCSPC at inference time if your hardware is fridndly to SPPFCSPC

相关推荐
AI街潜水的八角1 小时前
深度学习图像分类数据集—五种电器识别分类
人工智能·深度学习·分类
默辨1 小时前
机器学习(ML)、深度学习(DL)、强化学习(RL)关系和区别
人工智能·深度学习·机器学习
音程1 小时前
什么是Jaccard 相似度(Jaccard Similarity)
深度学习·数据挖掘
大模型最新论文速读2 小时前
指令微调时,也要考虑提示损失
人工智能·深度学习·语言模型·自然语言处理·llama
大千AI助手2 小时前
BERT:双向Transformer革命 | 重塑自然语言理解的预训练范式
人工智能·深度学习·机器学习·自然语言处理·llm·bert·transformer
看到我,请让我去学习3 小时前
OpenCV 图像进阶处理:特征提取与车牌识别深度解析
人工智能·opencv·计算机视觉
HuashuiMu花水木3 小时前
PyTorch笔记5----------Autograd、nn库
人工智能·pytorch·笔记
攻城狮7号3 小时前
阿里开源AI大模型ThinkSound如何为视频配上灵魂之声
人工智能·深度学习·开源模型·thinksound·阿里大模型
禺垣4 小时前
生成式对抗网络(GAN)模型原理概述
深度学习
阿群今天学习了吗4 小时前
pytorch环境配置
人工智能·pytorch·python·学习·机器学习