HorNet+YOLOv5改进方案-创新互联

HorNet理论请参考论文：https://arxiv.org/pdf/2207.14284.pdf

成都创新互联专注为客户提供全方位的互联网综合服务，包含不限于网站设计制作、成都网站制作、八公山网络推广、重庆小程序开发公司、八公山网络营销、八公山企业策划、八公山品牌公关、搜索引擎seo、人物专访、企业宣传片、企业代运营等，从售前售中售后，我们都将竭诚为您服务，您的肯定，是我们大的嘉奖；成都创新互联为所有大学生创业者提供八公山建站搭建服务，24小时服务热线：18982081108，官方网址：www.cdcxhl.com🚀yolov5加HorNet模块代码

1.在 common.py 文件中添加如下代码

部分代码如下

class Gnconv(nn.Module):
    def __init__(self, dim, order=5, gflayer=None, h=14, w=8, s=1.0):
        super().__init__()
        self.order = order
        self.dims = [dim // 2 ** i for i in range(order)]
        self.dims.reverse()
        self.proj_in = nn.Conv2d(dim, 2*dim, 1)
 
        if gflayer is None:
            self.dwconv = get_dwconv(sum(self.dims), 7, True)
        else:
            self.dwconv = gflayer(sum(self.dims), h=h, w=w)
        
        self.proj_out = nn.Conv2d(dim, dim, 1)
 
        self.pws = nn.ModuleList(
            [nn.Conv2d(self.dims[i], self.dims[i+1], 1) for i in range(order-1)]
        )
 
        self.scale = s
        print('[gnconv]', order, 'order with dims=', self.dims, 'scale=%.4f'%self.scale)

class GnBlock(nn.Module):
    def __init__(self, dim, shortcut=False, layer_scale_init_value=1e-6):
        super().__init__()
        self.shortcut = shortcut
        self.norm1 = LayerNorm(dim, eps=1e-6, data_format='channels_first')
        self.gnconv = GnConv(dim, dim)  # depthwise conv
        self.norm2 = LayerNorm(dim, eps=1e-6)
        self.pwconv1 = nn.Linear(dim, 2 * dim)  # pointwise/1x1 convs, implemented with linear layers
        self.act = nn.GELU()
        self.pwconv2 = nn.Linear(2 * dim, dim)
        self.gamma1 = nn.Parameter(layer_scale_init_value * torch.ones(dim),
                                   requires_grad=True) if layer_scale_init_value >0 else None

        self.gamma2 = nn.Parameter(layer_scale_init_value * torch.ones((dim)),
                                   requires_grad=True) if layer_scale_init_value >0 else None

    def forward(self, x):
        B, C, H, W = x.shape
        if self.gamma1 is not None:
            gamma1 = self.gamma1.view(C, 1, 1)
        else:
            gamma1 = 1
        x = (x + gamma1 * self.gnconv(self.norm1(x))) if self.shortcut else gamma1 * self.Gnconv(self.norm1(x))
        input = x
        x = x.permute(0, 2, 3, 1)  # (N, C, H, W) ->(N, H, W, C)
        x = self.norm2(x)
        x = self.pwconv1(x)
        x = self.act(x)
        x = self.pwconv2(x)
        if self.gamma2 is not None:
            x = self.gamma2 * x
        x = x.permute(0, 3, 1, 2)  # (N, H, W, C) ->(N, C, H, W)
        x = (input + x) if self.shortcut else x
        return x
        
class GNCSP(nn.Module):
    # CSP GnBlock with 3 GnConv
    def __init__(self, c1, c2, n=1, shortcut=True, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = GnConv(c1, c_, 3)
        self.cv2 = GnConv(c1, c_, 3)
        self.cv3 = GnConv(2 * c_, c2, 3)  # act=FReLU(c2)
        self.m = nn.Sequential(*[GnBlock(c_, shortcut) for _ in range(n)])

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

2.创建yolov5GNCSP.yaml配置文件

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicle
# Parameters
nc: 80  # 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, GnConv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, GNCSP, [512, False]],  # 13

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

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

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

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

3.在 models/yolo.py文件夹下找到parse_model函数

在459行 for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):下添加以下代码

elif m is GNCSP:
    c1, c2 = ch[f], args[0]
    if c2 != no:
        c2 = make_divisible(c2 * gw, 8)
 
    args = [c1, c2, *args[1:]]
    if m is GNCSP:
        args.insert(2, n)
        n = 1

你是否还在寻找稳定的海外服务器提供商？创新互联www.cdcxhl.cn海外机房具备T级流量清洗系统配攻击溯源，准确流量调度确保服务器高可用性，企业级服务器适合批量采购，新人活动首月15元起，快前往官网查看详情吧

网页名称：HorNet+YOLOv5改进方案-创新互联
转载注明：http://cqcxhl.com/article/degjde.html