Yolov7改进总结(1)——ACmix网络选取，卷积与自注意力的融合，涨点明显

ACmix网络理论简介

ACmix是卷积网络和transformer两种强大的网络优势的集合，具有较低的计算开销，同时也能提升网络性能，在卷积网络和transformer各行其是的今天，是一种融合两种优势的不错方法。

首先，通过使用1X1卷积对输入特征进行映射，获得丰富的中间特征集；
然后，按照不同的模式(分别以Self-Attention方式和卷积方式)重用和聚合中间特征。

主要贡献：
1.揭示了Self-Attention和卷积之间强大的潜在关系，为理解两个模块之间的联系提供了新的视角，并为设计新的学习范式提供了灵感;
2.介绍了Self-Attention和卷积模块的一个优雅集成，它享受这两者的优点。经验证据表明，混合模型始终优于其纯卷积或Self-Attention对应模型。
结论：
相比于普通卷积效果有所提升，但是相应计算量也比较大。
源码：

https://github.com/LeapLabTHU/ACmix

YOLOv7集成ACmix

修改结构配置yaml文件

新建一个yolov7_acmix.yaml文件，添加如下内容

# parameters
nc: 80  # number of classes
depth_multiple: 1.0  # 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
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, Conv, [64, 1, 1]],
   [-2, 1, Conv, [64, 1, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]],  # 11
         
   [-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]],  # 24
         
   [-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]],  # 29-P4/16  
   [-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]],  # 37
         
   [-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]],  # 42-P5/32  
   [-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]],  # 50
  ]

# yolov7 head
head:
  [[-1, 1, SPPCSPC, [512]], # 51
  
   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [37, 1, Conv, [256, 1, 1]], # route backbone P4
   [[-1, -2], 1, Concat, [1]],
   
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 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, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]], # 63
   
   [-1, 1, Conv, [128, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [24, 1, Conv, [128, 1, 1]], # route backbone P3
   [[-1, -2], 1, Concat, [1]],
   
   [-1, 1, Conv, [128, 1, 1]],
   [-2, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [128, 1, 1]], # 75
      
   [-1, 1, MP, []],
   [-1, 1, Conv, [128, 1, 1]],
   [-3, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 2]],
   [[-1, -3, 63], 1, Concat, [1]],
   
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 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, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]], # 88
      
   [-1, 1, MP, []],
   [-1, 1, Conv, [256, 1, 1]],
   [-3, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, -3, 51], 1, Concat, [1]],
   
   [-1, 1, Conv, [512, 1, 1]],
   [-2, 1, Conv, [512, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, ACmix, [256]], #9 修改
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [512, 1, 1]], # 101
   
   [75, 1, RepConv, [256, 3, 1]],
   [88, 1, RepConv, [512, 3, 1]],
   [101, 1, RepConv, [1024, 3, 1]],

   [[102,103,104], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
  ]

  # [-1, 1, ACmix, [1024]], #9

修改common.py文件

在./models/common.py文件中，添加以下内容

def position(H, W, is_cuda=True):
    if is_cuda:
        loc_w = torch.linspace(-1.0, 1.0, W).cuda().unsqueeze(0).repeat(H, 1)
        loc_h = torch.linspace(-1.0, 1.0, H).cuda().unsqueeze(1).repeat(1, W)
    else:
        loc_w = torch.linspace(-1.0, 1.0, W).unsqueeze(0).repeat(H, 1)
        loc_h = torch.linspace(-1.0, 1.0, H).unsqueeze(1).repeat(1, W)
    loc = torch.cat([loc_w.unsqueeze(0), loc_h.unsqueeze(0)], 0).unsqueeze(0)
    return loc


def stride(x, stride):
    b, c, h, w = x.shape
    return x[:, :, ::stride, ::stride]

def init_rate_half(tensor):
    if tensor is not None:
        tensor.data.fill_(0.5)

def init_rate_0(tensor):
    if tensor is not None:
        tensor.data.fill_(0.)


class ACmix(nn.Module):
    def __init__(self, in_planes, out_planes, kernel_att=7, head=4, kernel_conv=3, stride=1, dilation=1):
        super(ACmix, self).__init__()
        self.in_planes = in_planes
        self.out_planes = out_planes
        self.head = head
        self.kernel_att = kernel_att
        self.kernel_conv = kernel_conv
        self.stride = stride
        self.dilation = dilation
        self.rate1 = torch.nn.Parameter(torch.Tensor(1))
        self.rate2 = torch.nn.Parameter(torch.Tensor(1))
        self.head_dim = self.out_planes // self.head

        self.conv1 = nn.Conv2d(in_planes, out_planes, kernel_size=1)
        self.conv2 = nn.Conv2d(in_planes, out_planes, kernel_size=1)
        self.conv3 = nn.Conv2d(in_planes, out_planes, kernel_size=1)
        self.conv_p = nn.Conv2d(2, self.head_dim, kernel_size=1)

        self.padding_att = (self.dilation * (self.kernel_att - 1) + 1) // 2
        self.pad_att = torch.nn.ReflectionPad2d(self.padding_att)
        self.unfold = nn.Unfold(kernel_size=self.kernel_att, padding=0, stride=self.stride)
        self.softmax = torch.nn.Softmax(dim=1)

        self.fc = nn.Conv2d(3*self.head, self.kernel_conv * self.kernel_conv, kernel_size=1, bias=False)
        self.dep_conv = nn.Conv2d(self.kernel_conv * self.kernel_conv * self.head_dim, out_planes, kernel_size=self.kernel_conv, bias=True, groups=self.head_dim, padding=1, stride=stride)

        self.reset_parameters()
    
    def reset_parameters(self):
        init_rate_half(self.rate1)
        init_rate_half(self.rate2)
        kernel = torch.zeros(self.kernel_conv * self.kernel_conv, self.kernel_conv, self.kernel_conv)
        for i in range(self.kernel_conv * self.kernel_conv):
            kernel[i, i//self.kernel_conv, i%self.kernel_conv] = 1.
        kernel = kernel.squeeze(0).repeat(self.out_planes, 1, 1, 1)
        self.dep_conv.weight = nn.Parameter(data=kernel, requires_grad=True)
        self.dep_conv.bias = init_rate_0(self.dep_conv.bias)

    def forward(self, x):
        q, k, v = self.conv1(x), self.conv2(x), self.conv3(x)
        scaling = float(self.head_dim) ** -0.5
        b, c, h, w = q.shape
        h_out, w_out = h//self.stride, w//self.stride


        # ### att
        # ## positional encoding
        pe = self.conv_p(position(h, w, x.is_cuda))

        q_att = q.view(b*self.head, self.head_dim, h, w) * scaling
        k_att = k.view(b*self.head, self.head_dim, h, w)
        v_att = v.view(b*self.head, self.head_dim, h, w)

        if self.stride > 1:
            q_att = stride(q_att, self.stride)
            q_pe = stride(pe, self.stride)
        else:
            q_pe = pe

        unfold_k = self.unfold(self.pad_att(k_att)).view(b*self.head, self.head_dim, self.kernel_att*self.kernel_att, h_out, w_out) # b*head, head_dim, k_att^2, h_out, w_out
        unfold_rpe = self.unfold(self.pad_att(pe)).view(1, self.head_dim, self.kernel_att*self.kernel_att, h_out, w_out) # 1, head_dim, k_att^2, h_out, w_out
        
        att = (q_att.unsqueeze(2)*(unfold_k + q_pe.unsqueeze(2) - unfold_rpe)).sum(1) # (b*head, head_dim, 1, h_out, w_out) * (b*head, head_dim, k_att^2, h_out, w_out) -> (b*head, k_att^2, h_out, w_out)
        att = self.softmax(att)

        out_att = self.unfold(self.pad_att(v_att)).view(b*self.head, self.head_dim, self.kernel_att*self.kernel_att, h_out, w_out)
        out_att = (att.unsqueeze(1) * out_att).sum(2).view(b, self.out_planes, h_out, w_out)

        ## conv
        f_all = self.fc(torch.cat([q.view(b, self.head, self.head_dim, h*w), k.view(b, self.head, self.head_dim, h*w), v.view(b, self.head, self.head_dim, h*w)], 1))
        f_conv = f_all.permute(0, 2, 1, 3).reshape(x.shape[0], -1, x.shape[-2], x.shape[-1])
        
        out_conv = self.dep_conv(f_conv)

        return self.rate1 * out_att + self.rate2 * out_conv

修改yolo.py文件

在./models/yolo.py文件下里的parse_model函数，将ACmix类名添加上
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):内部对应位置，需要增加以下内容

		elif m in [ACmix]:
            c1, c2 = ch[f], args[0]
            if c2 != no:  # if not output
                c2 = make_divisible(c2 * gw, 8)
            args = [c1, c2, *args[1:]]

PS
出现RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the same

解决办法： 跑包含Acmix结构的网络，直接将test.py的half_precision参数改成false

利用yolov7_acmix.yaml训练模型

python train.py --cfg yolov7_acmix.yaml --acmix