YOLOv9改进策略 | 细节创新篇 | 迭代注意力特征融合AFF机制创新RepNCSPELAN4_注意力aff

​

import torch
import torch.nn as nn
import numpy as np
 
__all__ = ['RepNCSPELAN4_AFF']
 
class AFF(nn.Module):
    '''
    多特征融合 AFF
    '''
 
    def __init__(self, channels=64, r=2):
        super(AFF, self).__init__()
        inter_channels = int(channels // r)
 
        self.local_att = nn.Sequential(
            nn.Conv2d(channels, inter_channels, kernel_size=1, stride=1, padding=0),
            nn.BatchNorm2d(inter_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(inter_channels, channels, kernel_size=1, stride=1, padding=0),
            nn.BatchNorm2d(channels),
        )
 
        self.global_att = nn.Sequential(
            nn.Conv2d(channels, inter_channels, kernel_size=1, stride=1, padding=0),
            nn.BatchNorm2d(inter_channels),
            nn.ReLU(inplace=True),
            nn.Conv2d(inter_channels, channels, kernel_size=1, stride=1, padding=0),
            nn.BatchNorm2d(channels),
        )
 
        self.sigmoid = nn.Sigmoid()
 
    def forward(self, x, residual):
        xa = x + residual
        xl = self.local_att(xa)
        xg = self.global_att(xa)
        xlg = xl + xg
        wei = self.sigmoid(xlg)
 
        xo = 2 * x * wei + 2 * residual * (1 - wei)
        return xo
 
 
class RepConvN(nn.Module):
    """RepConv is a basic rep-style block, including training and deploy status
    This code is based on https://github.com/DingXiaoH/RepVGG/blob/main/repvgg.py
    """
    default_act = nn.SiLU()  # default activation
 
    def __init__(self, c1, c2, k=3, s=1, p=1, g=1, d=1, act=True, bn=False, deploy=False):
        super().__init__()
        assert k == 3 and p == 1
        self.g = g
        self.c1 = c1
        self.c2 = c2
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()
 
        self.bn = None
        self.conv1 = Conv(c1, c2, k, s, p=p, g=g, act=False)
        self.conv2 = Conv(c1, c2, 1, s, p=(p - k // 2), g=g, act=False)
 
    def forward_fuse(self, x):
        """Forward process"""
        return self.act(self.conv(x))
 
    def forward(self, x):
        """Forward process"""
        id_out = 0 if self.bn is None else self.bn(x)
        return self.act(self.conv1(x) + self.conv2(x) + id_out)
 
    def get_equivalent_kernel_bias(self):
        kernel3x3, bias3x3 = self._fuse_bn_tensor(self.conv1)
        kernel1x1, bias1x1 = self._fuse_bn_tensor(self.conv2)
        kernelid, biasid = self._fuse_bn_tensor(self.bn)
        return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid
 
    def _avg_to_3x3_tensor(self, avgp):
        channels = self.c1
        groups = self.g
        kernel_size = avgp.kernel_size
        input_dim = channels // groups
        k = torch.zeros((channels, input_dim, kernel_size, kernel_size))
        k[np.arange(channels), np.tile(np.arange(input_dim), groups), :, :] = 1.0 / kernel_size ** 2
        return k
 
    def _pad_1x1_to_3x3_tensor(self, kernel1x1):
        if kernel1x1 is None:
            return 0
        else:
            return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1])
 
    def _fuse_bn_tensor(self, branch):
        if branch is None:
            return 0, 0
        if isinstance(branch, Conv):
            kernel = branch.conv.weight
            running_mean = branch.bn.running_mean
            running_var = branch.bn.running_var
            gamma = branch.bn.weight
            beta = branch.bn.bias
            eps = branch.bn.eps
        elif isinstance(branch, nn.BatchNorm2d):
            if not hasattr(self, 'id_tensor'):
                input_dim = self.c1 // self.g
                kernel_value = np.zeros((self.c1, input_dim, 3, 3), dtype=np.float32)
                for i in range(self.c1):
                    kernel_value[i, i % input_dim, 1, 1] = 1
                self.id_tensor = torch.from_numpy(kernel_value).to(branch.weight.device)
            kernel = self.id_tensor
            running_mean = branch.running_mean
            running_var = branch.running_var
            gamma = branch.weight
            beta = branch.bias
            eps = branch.eps
        std = (running_var + eps).sqrt()
        t = (gamma / std).reshape(-1, 1, 1, 1)
        return kernel * t, beta - running_mean * gamma / std
 
    def fuse_convs(self):
        if hasattr(self, 'conv'):
            return
        kernel, bias = self.get_equivalent_kernel_bias()
        self.conv = nn.Conv2d(in_channels=self.conv1.conv.in_channels,
                              out_channels=self.conv1.conv.out_channels,
                              kernel_size=self.conv1.conv.kernel_size,
                              stride=self.conv1.conv.stride,
                              padding=self.conv1.conv.padding,
                              dilation=self.conv1.conv.dilation,
                              groups=self.conv1.conv.groups,
                              bias=True).requires_grad_(False)
        self.conv.weight.data = kernel
        self.conv.bias.data = bias
        for para in self.parameters():
            para.detach_()
        self.__delattr__('conv1')
        self.__delattr__('conv2')
        if hasattr(self, 'nm'):
            self.__delattr__('nm')
        if hasattr(self, 'bn'):
            self.__delattr__('bn')
        if hasattr(self, 'id_tensor'):
            self.__delattr__('id_tensor')
 
def autopad(k, p=None, d=1):  # kernel, padding, dilation
    # Pad to 'same' shape outputs
    if d > 1:
        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size
    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 with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)
    default_act = nn.SiLU()  # default activation
 
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = self.default_act 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)))
 
    def forward_fuse(self, x):
        return self.act(self.conv(x))
 
 
class RepNBottleneck_AFF(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):  # ch_in, ch_out, shortcut, kernels, groups, expand
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = RepConvN(c1, c_, k[0], 1)
        self.cv2 = Conv(c_, c2, k[1], 1, g=g)
        self.add = shortcut and c1 == c2
        self.AFF = AFF(c2)
    def forward(self, x):
        if self.add:
            results = self.AFF(x, self.cv2(self.cv1(x)))
        else:
            results = self.cv2(self.cv1(x))
        return results
 
 
class RepNCSP(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.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.Sequential(*(RepNBottleneck_AFF(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
 
    def forward(self, x):
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
 
 
class RepNCSPELAN4_AFF(nn.Module):
    # csp-elan
    def __init__(self, c1, c2, c3, c4, c5=1):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__()
        self.c = c3//2
        self.cv1 = Conv(c1, c3, 1, 1)
        self.cv2 = nn.Sequential(RepNCSP(c3//2, c4, c5), Conv(c4, c4, 3, 1))
        self.cv3 = nn.Sequential(RepNCSP(c4, c4, c5), Conv(c4, c4, 3, 1))
        self.cv4 = Conv(c3+(2*c4), c2, 1, 1)
 
    def forward(self, x):
        y = list(self.cv1(x).chunk(2, 1))
        y.extend((m(y[-1])) for m in [self.cv2, self.cv3])
        return self.cv4(torch.cat(y, 1))
 
    def forward_split(self, x):
        y = list(self.cv1(x).split((self.c, self.c), 1))
        y.extend(m(y[-1]) for m in [self.cv2, self.cv3])
        return self.cv4(torch.cat(y, 1))
 
 
if __name__ == '__main__':
    x1 = torch.randn(1, 32, 16, 16)
    x2 = torch.randn(1, 32, 16, 16)
    model = AFF(32)
    x = model(x1, x2)
    print(x.shape)

​

# YOLOv9
 
# parameters
nc: 80  # number of classes
depth_multiple: 1  # model depth multiple
width_multiple: 1  # layer channel multiple
#activation: nn.LeakyReLU(0.1)
#activation: nn.ReLU()
 
# anchors
anchors: 3
 
# YOLOv9 backbone
backbone:
  [
   [-1, 1, Silence, []],
   # conv down
   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
   # conv down
   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
   # elan-1 block
   [-1, 1, RepNCSPELAN4_AFF, [256, 128, 64, 1]],  # 3
   # conv down
   [-1, 1, Conv, [256, 3, 2]],  # 4-P3/8
   # elan-2 block
   [-1, 1, RepNCSPELAN4_AFF, [512, 256, 128, 1]],  # 5
   # conv down
   [-1, 1, Conv, [512, 3, 2]],  # 6-P4/16
   # elan-2 block
   [-1, 1, RepNCSPELAN4_AFF, [512, 512, 256, 1]],  # 7
   # conv down
   [-1, 1, Conv, [512, 3, 2]],  # 8-P5/32
   # elan-2 block
   [-1, 1, RepNCSPELAN4_AFF, [512, 512, 256, 1]],  # 9
  ]
 
# YOLOv9 head
head:
  [
   # elan-spp block
   [-1, 1, SPPELAN, [512, 256]],  # 10
 
   # up-concat merge
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 7], 1, Concat, [1]],  # cat backbone P4
 
   # elan-2 block
   [-1, 1, RepNCSPELAN4_AFF, [512, 512, 256, 1]],  # 13
 
   # up-concat merge
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 5], 1, Concat, [1]],  # cat backbone P3
 
   # elan-2 block
   [-1, 1, RepNCSPELAN4_AFF, [256, 256, 128, 1]],  # 16 (P3/8-small)
 
   # conv-down merge
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 13], 1, Concat, [1]],  # cat head P4
 
   # elan-2 block
   [-1, 1, RepNCSPELAN4_AFF, [512, 512, 256, 1]],  # 19 (P4/16-medium)
 
   # conv-down merge
   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
 
   # elan-2 block
   [-1, 1, RepNCSPELAN4_AFF, [512, 512, 256, 1]],  # 22 (P5/32-large)
   
   # routing
   [5, 1, CBLinear, [[256]]], # 23
   [7, 1, CBLinear, [[256, 512]]], # 24
   [9, 1, CBLinear, [[256, 512, 512]]], # 25
   
   # conv down
   [0, 1, Conv, [64, 3, 2]],  # 26-P1/2
 
   # conv down
   [-1, 1, Conv, [128, 3, 2]],  # 27-P2/4
 
   # elan-1 block
   [-1, 1, RepNCSPELAN4_AFF, [256, 128, 64, 1]],  # 28
 
   # conv down fuse
   [-1, 1, Conv, [256, 3, 2]],  # 29-P3/8
   [[23, 24, 25, -1], 1, CBFuse, [[0, 0, 0]]], # 30  
 
   # elan-2 block
   [-1, 1, RepNCSPELAN4_AFF, [512, 256, 128, 1]],  # 31
 
   # conv down fuse
   [-1, 1, Conv, [512, 3, 2]],  # 32-P4/16
   [[24, 25, -1], 1, CBFuse, [[1, 1]]], # 33 
 
   # elan-2 block
   [-1, 1, RepNCSPELAN4_AFF, [512, 512, 256, 1]],  # 34
 
   # conv down fuse
   [-1, 1, Conv, [512, 3, 2]],  # 35-P5/32
   [[25, -1], 1, CBFuse, [[2]]], # 36
 
   # elan-2 block
   [-1, 1, RepNCSPELAN4_AFF, [512, 512, 256, 1]],  # 37
 
   # detect
   [[31, 34, 37, 16, 19, 22], 1, DualDDetect, [nc]],  # DualDDetect(A3, A4, A5, P3, P4, P5)
  ]