365天深度学习训练营-第P9周-YOLOv5-Backbone模块实现

本文为365天深度学习训练营 中的学习记录博客
原作者：K同学啊|接辅导、项目定制

---

任务：

• 利用yolov5 Backbone 搭建图像分类网络
• 学习Backbone结构中的细节，思考设计理由

一、Backbone模块

• YOLOv5 的backbone由多个标准卷积以及C3结构组成，这两个结构上周已经详细分析过了
• 这周的重点是SPPF

空间金字塔池化（SPP）

• 论文地址：Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

#coding=utf-8

import math
import torch
import torch.nn.functional as F

# 构建SPP层(空间金字塔池化层)
class SPPLayer(torch.nn.Module):

    def __init__(self, num_levels, pool_type='max_pool'):
        super(SPPLayer, self).__init__()

        self.num_levels = num_levels
        self.pool_type = pool_type

    def forward(self, x):
        num, c, h, w = x.size() # num:样本数量 c:通道数 h:高 w:宽
        for i in range(self.num_levels):
            level = i+1
            kernel_size = (math.ceil(h / level), math.ceil(w / level))
            stride = (math.ceil(h / level), math.ceil(w / level))
            pooling = (math.floor((kernel_size[0]*level-h+1)/2), math.floor((kernel_size[1]*level-w+1)/2))

            # 选择池化方式 
            if self.pool_type == 'max_pool':
                tensor = F.max_pool2d(x, kernel_size=kernel_size, stride=stride, padding=pooling).view(num, -1)
            else:
                tensor = F.avg_pool2d(x, kernel_size=kernel_size, stride=stride, padding=pooling).view(num, -1)

            # 展开、拼接
            if (i == 0):
                x_flatten = tensor.view(num, -1)
            else:
                x_flatten = torch.cat((x_flatten, tensor.view(num, -1)), 1)
        return x_flatten

• SPPF

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)#先通过CBL进行通道数的减半
        with warnings.catch_warnings():
            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
            y1 = self.m(x)
            y2 = self.m(y1)
            #上述两次最大池化
            return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
            #将原来的x,一次池化后的y1,两次池化后的y2,3次池化的self.m(y2)先进行拼接，然后再CBL

二、代码

• 除了主干网络有所不同其余部分均相同

构建YOLOv5 Backbone

C3结构

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, shorcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e) # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1, g=g)
        self.cv3 = Conv(2 * c_, c2, 1) # act = FReLU(c2)
        self.main = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
        
    def forward(self, x):
        return self.cv3(torch.cat((self.main(self.cv1(x)), self.cv2(x)), dim=1))

SPPF

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)#先通过CBL进行通道数的减半
        with warnings.catch_warnings():
            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
            y1 = self.m(x)
            y2 = self.m(y1)
            #上述两次最大池化
            return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
            #将原来的x,一次池化后的y1,两次池化后的y2,3次池化的self.m(y2)先进行拼接，然后再CBL

• 总网络结构：

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)
        self.Conv_4 = Conv(128, 256, 3, 2)
        self.c3_5 = Conv(256, 256)
        self.Conv_6 = Conv(256, 512, 3, 2)
        self.c3_7 = C3(512, 512)
        self.Conv_8 = Conv(512, 1024, 3, 2)
        self.c3_9 = C3(1024, 1024)
        self.SPPF = SPPF(1024, 1024, 5)
        
        self.fc = nn.Sequential(
            nn.Linear(in_features=65536, out_features=100),
            nn.ReLU(),
            nn.Linear(100, 4)
        )
        
    def forward(self, x):
        x = self.c3_3(self.Conv_2(self.Conv_1(x)))
        x = self.c3_5(self.Conv_4(x))
        x = self.c3_7(self.Conv_6(x))
        x = self.c3_9(self.Conv_8(x))
        
        x = self.SPPF(x)
        
        x = torch.flatten(x, start_dim=1)
        x = self.fc(x)
        return x

训练

误差可视化

预测

备注：最近在写论文，问题留到论文投稿后统一解决

---

参考：
空间金字塔池化(Spatial Pyramid Pooling, SPP)原理和代码实现(Pytorch)
YOLOv5网络详解