yolov7添加GAMAttention注意力机制,同时添加CNeB,C3C2

1,common.py配置

./models/common.py文件增加以下模块

class GAMAttention(nn.Module):
       #https://paperswithcode.com/paper/global-attention-mechanism-retain-information
    def __init__(self, c1, c2, group=True,rate=4):
        super(GAMAttention, self).__init__()
        
        self.channel_attention = nn.Sequential(
            nn.Linear(c1, int(c1 / rate)),
            nn.ReLU(inplace=True),
            nn.Linear(int(c1 / rate), c1)
        )
        self.spatial_attention = nn.Sequential(
            nn.Conv2d(c1, c1//rate, kernel_size=7, padding=3,groups=rate)if group else nn.Conv2d(c1, int(c1 / rate), kernel_size=7, padding=3), 
            nn.BatchNorm2d(int(c1 /rate)),
            nn.ReLU(inplace=True),
            nn.Conv2d(c1//rate, c2, kernel_size=7, padding=3,groups=rate) if group else nn.Conv2d(int(c1 / rate), c2, kernel_size=7, padding=3), 
            nn.BatchNorm2d(c2)
        )

    def forward(self, x):
        b, c, h, w = x.shape
        x_permute = x.permute(0, 2, 3, 1).view(b, -1, c)
        x_att_permute = self.channel_attention(x_permute).view(b, h, w, c)
        x_channel_att = x_att_permute.permute(0, 3, 1, 2)
        x = x * x_channel_att
 
        x_spatial_att = self.spatial_attention(x).sigmoid()
        x_spatial_att=channel_shuffle(x_spatial_att,4) #last shuffle 
        out = x * x_spatial_att
        return out  

def channel_shuffle(x, groups=2):
        B, C, H, W = x.size()
        out = x.view(B, groups, C // groups, H, W).permute(0, 2, 1, 3, 4).contiguous()
        out=out.view(B, C, H, W) 
        return out

在yolo.py中添加:

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

2,添加添加CNeB模块代码:

common.py 文件中添加如下代码

class LayerNorm_s(nn.Module):
    
    def __init__(self, normalized_shape, eps=1e-6, data_format="channels_last"):
        super().__init__()
        self.weight = nn.Parameter(torch.ones(normalized_shape))
        self.bias = nn.Parameter(torch.zeros(normalized_shape))
        self.eps = eps
        self.data_format = data_format
        if self.data_format not in ["channels_last", "channels_first"]:
            raise NotImplementedError
        self.normalized_shape = (normalized_shape,)
 
    def forward(self, x):
        if self.data_format == "channels_last":
            return F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
        elif self.data_format == "channels_first":
            u = x.mean(1, keepdim=True)
            s = (x - u).pow(2).mean(1, keepdim=True)
            x = (x - u) / torch.sqrt(s + self.eps)
            x = self.weight[:, None, None] * x + self.bias[:, None, None]
            return x
 
class ConvNextBlock(nn.Module):
    
    def __init__(self, dim, drop_path=0., layer_scale_init_value=1e-6):
        super().__init__()
        self.dwconv = nn.Conv2d(dim, dim, kernel_size=7, padding=3, groups=dim)  # depthwise conv
        self.norm = LayerNorm_s(dim, eps=1e-6)
        self.pwconv1 = nn.Linear(dim, 4 * dim)  
        self.act = nn.GELU()
        self.pwconv2 = nn.Linear(4 * dim, dim)
        self.gamma = nn.Parameter(layer_scale_init_value * torch.ones((dim)),
                                  requires_grad=True) if layer_scale_init_value > 0 else None
        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
 
    def forward(self, x):
        input = x
        x = self.dwconv(x)
        x = x.permute(0, 2, 3, 1)  # (N, C, H, W) -> (N, H, W, C)
        x = self.norm(x)
        x = self.pwconv1(x)
        x = self.act(x)
        x = self.pwconv2(x)
        if self.gamma is not None:
            x = self.gamma * x
        x = x.permute(0, 3, 1, 2)  # (N, H, W, C) -> (N, C, H, W)
 
        x = input + self.drop_path(x)
        return x
 
class DropPath(nn.Module):
    """Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks).
    """
 
    def __init__(self, drop_prob=None):
        super(DropPath, self).__init__()
        self.drop_prob = drop_prob
 
    def forward(self, x):
        return drop_path_f(x, self.drop_prob, self.training)
 
def drop_path_f(x, drop_prob: float = 0., training: bool = False):
    if drop_prob == 0. or not training:
        return x
    keep_prob = 1 - drop_prob
    shape = (x.shape[0],) + (1,) * (x.ndim - 1)  # work with diff dim tensors, not just 2D ConvNets
    random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
    random_tensor.floor_()  # binarize
    output = x.div(keep_prob) * random_tensor
    return output
 
 
class CNeB(nn.Module):
    # CSP ConvNextBlock with 3 convolutions by iscyy/yoloair
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)
        self.m = nn.Sequential(*(ConvNextBlock(c_) for _ in range(n)))
    def forward(self, x):
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))

在 models/yolo.py文件夹下找到parse_model函数

for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):``下方添加以下代码

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

3,添加C3C2模块:

在common.py中添加:

class C3C2(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, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.conv = nn.Conv2d(c1, c_, 1, 1, autopad(1, None), groups=g, bias=False)
        self.bn = nn.BatchNorm2d(c_)
        self.act = nn.SiLU()
        self.cv1 = Conv(2 * c_, c2, 1, act=nn.Mish())
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))

    def forward(self, x):
        y = self.conv(x)
        return self.cv1(torch.cat((self.m(self.act(self.bn(y))), y), dim=1))

在yolo.py中添加:

4,更改配置文件

# YOLOv7 🚀, GPL-3.0 license
# parameters
nc: 4  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 1.0  # layer channel multiple

# anchors
anchors:
  - [12,16, 19,36, 40,28]  # P3/8
  - [36,75, 76,55, 72,146]  # P4/16
  - [142,110, 192,243, 459,401]  # P5/32

# yolov7 backbone by yoloair
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [32, 3, 1]],  # 0
   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
   [-1, 1, CNeB, [128]],
   [-1, 1, Conv, [256, 3, 2]],
   [-1, 1, MP, []],
   [-1, 1, Conv, [128, 1, 1]],
   [-3, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 16-P3/8
   [-1, 1, Conv, [128, 1, 1]],
   [-2, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [512, 1, 1]],
   [-1, 1, MP, []],
   [-1, 1, Conv, [256, 1, 1]],
   [-3, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, -3], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [1024, 1, 1]],
   [-1, 1, MP, []],
   [-1, 1, Conv, [512, 1, 1]],
   [-3, 1, Conv, [512, 1, 1]],
   [-1, 1, Conv, [512, 3, 2]],
   [[-1, -3], 1, Concat, [1]],
   [-1, 1, CNeB, [1024]],
   [-1, 1, Conv, [256, 3, 1]],
  ]

# yolov7 head by yoloair
head:
  [[-1, 1, SPPCSPC, [512]],
   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [31, 1, Conv, [256, 1, 1]],
   [[-1, -2], 1, Concat, [1]],
   [-1, 1, C3C2, [128]],
   [-1, 1, Conv, [128, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [18, 1, Conv, [128, 1, 1]],
   [[-1, -2], 1, Concat, [1]],
   [-1, 1, C3C2, [128]],
   [-1, 1, MP, []],
   [-1, 1, Conv, [128, 1, 1]],
   [-3, 1, GAMAttention, [128]],
   [-1, 1, Conv, [128, 3, 2]],
   [[-1, -3, 44], 1, Concat, [1]],
   [-1, 1, C3C2, [256]],
   [-1, 1, MP, []],
   [-1, 1, Conv, [256, 1, 1]],
   [-3, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, -3, 39], 1, Concat, [1]],
   [-1, 3, C3C2, [512]],

# 检测头 -----------------------------
   [49, 1, RepConv, [256, 3, 1]],
   [55, 1, RepConv, [512, 3, 1]],
   [61, 1, RepConv, [1024, 3, 1]],

   [[62,63,64], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
  ]

如果是mish的错误就是pytorch版本不对(重新建一个环境):

pip install torch==1.12.0+cu113 torchvision==0.13.0+cu113 --extra-index-url https://download.pytorch.org/whl/cu113

相关推荐
2401_857439691 小时前
SSM 架构下 Vue 电脑测评系统:为电脑性能评估赋能
开发语言·php
SoraLuna1 小时前
「Mac畅玩鸿蒙与硬件47」UI互动应用篇24 - 虚拟音乐控制台
开发语言·macos·ui·华为·harmonyos
xlsw_2 小时前
java全栈day20--Web后端实战(Mybatis基础2)
java·开发语言·mybatis
梧桐树04292 小时前
python常用内建模块:collections
python
Dream_Snowar3 小时前
速通Python 第三节
开发语言·python
高山我梦口香糖3 小时前
[react]searchParams转普通对象
开发语言·前端·javascript
信号处理学渣4 小时前
matlab画图,选择性显示legend标签
开发语言·matlab
红龙创客4 小时前
某狐畅游24校招-C++开发岗笔试(单选题)
开发语言·c++
蓝天星空4 小时前
Python调用open ai接口
人工智能·python
jasmine s4 小时前
Pandas
开发语言·python