YOLOv5改进系列：轻量化GSConv助力降参提点

一、GSConv论文理论

论文地址：Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles

1.理论思想

本文引入了一种新方法 GSConv 来减轻模型的复杂度并保持准确性。GSConv 可以更好地平衡模型的准确性和速度。并且，提供了一种设计范式，Slim-Neck，以实现检测器更高的计算成本效益。

2.创新点

1)引入了一种新方法 GSConv 来代替 SC 操作。该方法使卷积计算的输出尽可能接近 SC，同时降低计算成本；

2)为自动驾驶汽车的检测器架构提供了一种新的设计范式，即带有标准 Backbone 的 Slim-Neck 设计；

操作过程：

1)输入进行一个普通卷积的下采样

2)对上一步的输出使用DWConv深度卷积

3）将两个conv的结果拼接起来

4）进行shuffle操作 

二、代码部署

1.代码

# ---------------------------- GSConv ---------------------------------
class GSConv(nn.Module):
    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):
        super().__init__()
        c_ = c2 // 2
        self.cv1 = Conv(c1, c_, k, s, None, g, act)
        self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)

    def forward(self, x):
        x1 = self.cv1(x)
        x2 = torch.cat((x1, self.cv2(x1)), 1)
        # shuffle
        # y = x2.reshape(x2.shape[0], 2, x2.shape[1] // 2, x2.shape[2], x2.shape[3])
        # y = y.permute(0, 2, 1, 3, 4)
        # return y.reshape(y.shape[0], -1, y.shape[3], y.shape[4])

        b, n, h, w = x2.data.size()
        b_n = b * n // 2
        y = x2.reshape(b_n, 2, h * w)
        y = y.permute(1, 0, 2)
        y = y.reshape(2, -1, n // 2, h, w)

        return torch.cat((y[0], y[1]), 1)


class GSConvns(GSConv):
    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):
        super().__init__(c1, c2, k=1, s=1, g=1, act=True)
        c_ = c2 // 2
        self.shuf = nn.Conv2d(c_ * 2, c2, 1, 1, 0, bias=False)

    def forward(self, x):
        x1 = self.cv1(x)
        x2 = torch.cat((x1, self.cv2(x1)), 1)
        # normative-shuffle, TRT supported
        return nn.ReLU(self.shuf(x2))


class GSBottleneck(nn.Module):
    def __init__(self, c1, c2, k=3, s=1):
        super().__init__()
        c_ = c2 // 2
        # for lighting
        self.conv_lighting = nn.Sequential(
            GSConv(c1, c_, 1, 1),
            GSConv(c_, c2, 1, 1, act=False))
        # for receptive field
        self.conv = nn.Sequential(
            GSConv(c1, c_, 3, 1),
            GSConv(c_, c2, 3, 1, act=False))
        self.shortcut = Conv(c1, c2, 3, 1, act=False)

    def forward(self, x):
        return self.conv_lighting(x) + self.shortcut(x)


class DWConv(Conv):
    # Depth-wise convolution
    def __init__(self, c1, c2, k=1, s=1, d=1, act=True):  # ch_in, ch_out, kernel, stride, dilation, activation
        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)


class GSBottleneckC(GSBottleneck):
    def __init__(self, c1, c2, k=3, s=1):
        super().__init__(c1, c2, k, s)
        self.shortcut = DWConv(c1, c2, 3, 1, act=False)


class VoVGSCSP(nn.Module):
    # VoVGSCSP module with GSBottleneck
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        # self.gc1 = GSConv(c_, c_, 1, 1)
        # self.gc2 = GSConv(c_, c_, 1, 1)
        self.gsb = GSBottleneck(c_, c_, 1, 1)
        self.res = Conv(c_, c_, 3, 1, act=False)
        self.cv3 = Conv(2 * c_, c2, 1)  #

    def forward(self, x):
        x1 = self.gsb(self.cv1(x))
        y = self.cv2(x)
        return self.cv3(torch.cat((y, x1), dim=1))


class VoVGSCSPC(nn.Module):
    # cheap VoVGSCSP module with GSBottleneck
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.gsb = GSBottleneckC(c_, c_, 1, 1)
# ---------------------------- end ---------------------------------

2.配置教程

（1）在models/cmmon.py中添加上述代码

（2）在models/yolo.py中添加GSConv,VoVGSCSP, VoVGSCSPC，如下图所示

VoVGSCSP, VoVGSCSPC

3.yaml文件

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicle
# Parameters
nc: 1  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# 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
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, GSConv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, GSConv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, GSConv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, GSConv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

三、总结

本文主要工作包括GSConv原理介绍及提供GSConv改进代码策略，该模块为即插即用模块，部署位置可根据实际针对任务需求，自行调整。

本专栏持续更新中，订阅本栏，关注更新~