专栏介绍：YOLOv9改进系列 | 包含深度学习最新创新，主力高效涨点！！！
一、改进点介绍
AKConv是一种具有任意数量的参数和任意采样形状的可变卷积核，对不规则特征有更好的提取效果。
论文速览：：AKConv是2023年11月发表的一种可变卷积核，赋予卷积核任意数量的参数和任意采样形状，以解决具有固定样本形状和正方形的卷积核不能很好地适应不断变化的目标的问题点可以为网络开销和性能之间的权衡提供更丰富的选择。 AKConv的核心思想在于它为卷积核提供了任意数量的参数和任意采样形状，能够使用任意数量的参数(如1,2,3,4,5,6,7等)来提取姝征，这在标准卷积和可变形卷积Q中并未实现。AKConv能够根据硬件环境，使卷积参数的数星呈线性增减（(非常适用于轻量化模型)。
适用检测目标： 通用改进
二、AKConv模块详解
论文地址： https://arxiv.org/abs/2311.11587
代码地址： https://github.com/CV-ZhangXin/AKConv/tree/main
2.1 模块简介
AKConv的主要思想： 使用可变形状和大小的卷积核提升模型的特征提取能力。
AKConv的主要创新点： 1.对于不同大小的卷积核，作者提出了一种算法来生成任意大小卷积核的初始采样坐标。2.为了适应目标的不同变化，作者通过获得的偏移量来调整不规则卷积核的采样位置。3.与常规卷积核相比，所提出的AKConv实现了不规则卷积核提取特征的功能，为各种不同的目标提供了任意采样形状和大小的卷积核，弥补了常规卷积的不足。
点评： 简单点说，作者通过一定的方法做出了一种任意形状的卷积核，对不规则特征具有很强的提取能力，感兴趣的同学可以去阅读源码！
AKConv模块的原理图
三、AKConv模块使用教程
3.1 AKConv模块的代码
class AKConv(nn.Module):
def __init__(self, inc, outc, num_param=5, stride=1, bias=None):
"""
初始化参数说明：
inc: 输入通道数, outc: 输出通道数, num_param:（卷积核）参数量, stride = 1:卷积步长默认为1, bias = None：默认无偏执
"""
super(AKConv, self).__init__()
self.num_param = num_param
self.stride = stride
self.conv = Conv(inc, outc, k=(num_param, 1), s=(num_param, 1), b=bias)
self.p_conv = nn.Conv2d(inc, 2 * num_param, kernel_size=3, padding=1, stride=stride)
nn.init.constant_(self.p_conv.weight, 0)
self.p_conv.register_full_backward_hook(self._set_lr)
@staticmethod
def _set_lr(module, grad_input, grad_output):
grad_input = (grad_input[i] * 0.1 for i in range(len(grad_input)))
grad_output = (grad_output[i] * 0.1 for i in range(len(grad_output)))
def forward(self, x):
# N is num_param.
offset = self.p_conv(x)
dtype = offset.data.type()
N = offset.size(1) // 2
# (b, 2N, h, w)
p = self._get_p(offset, dtype)
# (b, h, w, 2N)
p = p.contiguous().permute(0, 2, 3, 1)
q_lt = p.detach().floor()
q_rb = q_lt + 1
q_lt = torch.cat([torch.clamp(q_lt[..., :N], 0, x.size(2) - 1), torch.clamp(q_lt[..., N:], 0, x.size(3) - 1)],
dim=-1).long()
q_rb = torch.cat([torch.clamp(q_rb[..., :N], 0, x.size(2) - 1), torch.clamp(q_rb[..., N:], 0, x.size(3) - 1)],
dim=-1).long()
q_lb = torch.cat([q_lt[..., :N], q_rb[..., N:]], dim=-1)
q_rt = torch.cat([q_rb[..., :N], q_lt[..., N:]], dim=-1)
# clip p
p = torch.cat([torch.clamp(p[..., :N], 0, x.size(2) - 1), torch.clamp(p[..., N:], 0, x.size(3) - 1)], dim=-1)
# bilinear kernel (b, h, w, N)
g_lt = (1 + (q_lt[..., :N].type_as(p) - p[..., :N])) * (1 + (q_lt[..., N:].type_as(p) - p[..., N:]))
g_rb = (1 - (q_rb[..., :N].type_as(p) - p[..., :N])) * (1 - (q_rb[..., N:].type_as(p) - p[..., N:]))
g_lb = (1 + (q_lb[..., :N].type_as(p) - p[..., :N])) * (1 - (q_lb[..., N:].type_as(p) - p[..., N:]))
g_rt = (1 - (q_rt[..., :N].type_as(p) - p[..., :N])) * (1 + (q_rt[..., N:].type_as(p) - p[..., N:]))
# resampling the features based on the modified coordinates.
x_q_lt = self._get_x_q(x, q_lt, N)
x_q_rb = self._get_x_q(x, q_rb, N)
x_q_lb = self._get_x_q(x, q_lb, N)
x_q_rt = self._get_x_q(x, q_rt, N)
# bilinear
x_offset = g_lt.unsqueeze(dim=1) * x_q_lt + \
g_rb.unsqueeze(dim=1) * x_q_rb + \
g_lb.unsqueeze(dim=1) * x_q_lb + \
g_rt.unsqueeze(dim=1) * x_q_rt
x_offset = self._reshape_x_offset(x_offset, self.num_param)
out = self.conv(x_offset)
return out
# generating the inital sampled shapes for the AKConv with different sizes.
def _get_p_n(self, N, dtype):
base_int = round(math.sqrt(self.num_param))
row_number = self.num_param // base_int
mod_number = self.num_param % base_int
p_n_x, p_n_y = torch.meshgrid(
torch.arange(0, row_number),
torch.arange(0, base_int), indexing='xy')
p_n_x = torch.flatten(p_n_x)
p_n_y = torch.flatten(p_n_y)
if mod_number > 0:
mod_p_n_x, mod_p_n_y = torch.meshgrid(
torch.arange(row_number, row_number + 1),
torch.arange(0, mod_number), indexing='xy')
mod_p_n_x = torch.flatten(mod_p_n_x)
mod_p_n_y = torch.flatten(mod_p_n_y)
p_n_x, p_n_y = torch.cat((p_n_x, mod_p_n_x)), torch.cat((p_n_y, mod_p_n_y))
p_n = torch.cat([p_n_x, p_n_y], 0)
p_n = p_n.view(1, 2 * N, 1, 1).type(dtype)
return p_n
# no zero-padding
def _get_p_0(self, h, w, N, dtype):
p_0_x, p_0_y = torch.meshgrid(
torch.arange(0, h * self.stride, self.stride),
torch.arange(0, w * self.stride, self.stride), indexing='xy')
p_0_x = torch.flatten(p_0_x).view(1, 1, h, w).repeat(1, N, 1, 1)
p_0_y = torch.flatten(p_0_y).view(1, 1, h, w).repeat(1, N, 1, 1)
p_0 = torch.cat([p_0_x, p_0_y], 1).type(dtype)
return p_0
def _get_p(self, offset, dtype):
N, h, w = offset.size(1) // 2, offset.size(2), offset.size(3)
# (1, 2N, 1, 1)
p_n = self._get_p_n(N, dtype)
# (1, 2N, h, w)
p_0 = self._get_p_0(h, w, N, dtype)
p = p_0 + p_n + offset
return p
def _get_x_q(self, x, q, N):
b, h, w, _ = q.size()
padded_w = x.size(3)
c = x.size(1)
# (b, c, h*w)
x = x.contiguous().view(b, c, -1)
# (b, h, w, N)
index = q[..., :N] * padded_w + q[..., N:] # offset_x*w + offset_y
# (b, c, h*w*N)
index = index.contiguous().unsqueeze(dim=1).expand(-1, c, -1, -1, -1).contiguous().view(b, c, -1)
x_offset = x.gather(dim=-1, index=index).contiguous().view(b, c, h, w, N)
return x_offset
# Stacking resampled features in the row direction.
@staticmethod
def _reshape_x_offset(x_offset, num_param):
b, c, h, w, n = x_offset.size()
x_offset = rearrange(x_offset, 'b c h w n -> b c (h n) w')
return x_offset3.2 在YOlO v9中的添加教程
阅读YOLOv9添加模块教程或使用下文操作
YOLOv9添加模块教程
1. 将YOLOv9工程中models下common.py文件中代码增加下文中的代码。
from einops import rearrange
class AKConv(nn.Module):
def __init__(self, inc, outc, num_param=5, stride=1):
"""
初始化参数说明：
inc: 输入通道数, outc: 输出通道数, num_param:（卷积核）参数量, stride = 1:卷积步长默认为1, bias = None：默认无偏执
"""
super(AKConv, self).__init__()
self.num_param = num_param
self.stride = stride
self.conv = Conv(inc, outc, k=(num_param, 1), s=(num_param, 1) )
self.p_conv = nn.Conv2d(inc, 2 * num_param, kernel_size=3, padding=1, stride=stride)
nn.init.constant_(self.p_conv.weight, 0)
self.p_conv.register_full_backward_hook(self._set_lr)
@staticmethod
def _set_lr(module, grad_input, grad_output):
grad_input = (grad_input[i] * 0.1 for i in range(len(grad_input)))
grad_output = (grad_output[i] * 0.1 for i in range(len(grad_output)))
def forward(self, x):
# N is num_param.
offset = self.p_conv(x)
dtype = offset.data.type()
N = offset.size(1) // 2
# (b, 2N, h, w)
p = self._get_p(offset, dtype)
# (b, h, w, 2N)
p = p.contiguous().permute(0, 2, 3, 1)
q_lt = p.detach().floor()
q_rb = q_lt + 1
q_lt = torch.cat([torch.clamp(q_lt[..., :N], 0, x.size(2) - 1), torch.clamp(q_lt[..., N:], 0, x.size(3) - 1)],
dim=-1).long()
q_rb = torch.cat([torch.clamp(q_rb[..., :N], 0, x.size(2) - 1), torch.clamp(q_rb[..., N:], 0, x.size(3) - 1)],
dim=-1).long()
q_lb = torch.cat([q_lt[..., :N], q_rb[..., N:]], dim=-1)
q_rt = torch.cat([q_rb[..., :N], q_lt[..., N:]], dim=-1)
# clip p
p = torch.cat([torch.clamp(p[..., :N], 0, x.size(2) - 1), torch.clamp(p[..., N:], 0, x.size(3) - 1)], dim=-1)
# bilinear kernel (b, h, w, N)
g_lt = (1 + (q_lt[..., :N].type_as(p) - p[..., :N])) * (1 + (q_lt[..., N:].type_as(p) - p[..., N:]))
g_rb = (1 - (q_rb[..., :N].type_as(p) - p[..., :N])) * (1 - (q_rb[..., N:].type_as(p) - p[..., N:]))
g_lb = (1 + (q_lb[..., :N].type_as(p) - p[..., :N])) * (1 - (q_lb[..., N:].type_as(p) - p[..., N:]))
g_rt = (1 - (q_rt[..., :N].type_as(p) - p[..., :N])) * (1 + (q_rt[..., N:].type_as(p) - p[..., N:]))
# resampling the features based on the modified coordinates.
x_q_lt = self._get_x_q(x, q_lt, N)
x_q_rb = self._get_x_q(x, q_rb, N)
x_q_lb = self._get_x_q(x, q_lb, N)
x_q_rt = self._get_x_q(x, q_rt, N)
# bilinear
x_offset = g_lt.unsqueeze(dim=1) * x_q_lt + \
g_rb.unsqueeze(dim=1) * x_q_rb + \
g_lb.unsqueeze(dim=1) * x_q_lb + \
g_rt.unsqueeze(dim=1) * x_q_rt
x_offset = self._reshape_x_offset(x_offset, self.num_param)
out = self.conv(x_offset)
return out
# generating the inital sampled shapes for the AKConv with different sizes.
def _get_p_n(self, N, dtype):
base_int = round(math.sqrt(self.num_param))
row_number = self.num_param // base_int
mod_number = self.num_param % base_int
p_n_x, p_n_y = torch.meshgrid(
torch.arange(0, row_number),
torch.arange(0, base_int), indexing='xy')
p_n_x = torch.flatten(p_n_x)
p_n_y = torch.flatten(p_n_y)
if mod_number > 0:
mod_p_n_x, mod_p_n_y = torch.meshgrid(
torch.arange(row_number, row_number + 1),
torch.arange(0, mod_number), indexing='xy')
mod_p_n_x = torch.flatten(mod_p_n_x)
mod_p_n_y = torch.flatten(mod_p_n_y)
p_n_x, p_n_y = torch.cat((p_n_x, mod_p_n_x)), torch.cat((p_n_y, mod_p_n_y))
p_n = torch.cat([p_n_x, p_n_y], 0)
p_n = p_n.view(1, 2 * N, 1, 1).type(dtype)
return p_n
# no zero-padding
def _get_p_0(self, h, w, N, dtype):
p_0_x, p_0_y = torch.meshgrid(
torch.arange(0, h * self.stride, self.stride),
torch.arange(0, w * self.stride, self.stride), indexing='xy')
p_0_x = torch.flatten(p_0_x).view(1, 1, h, w).repeat(1, N, 1, 1)
p_0_y = torch.flatten(p_0_y).view(1, 1, h, w).repeat(1, N, 1, 1)
p_0 = torch.cat([p_0_x, p_0_y], 1).type(dtype)
return p_0
def _get_p(self, offset, dtype):
N, h, w = offset.size(1) // 2, offset.size(2), offset.size(3)
# (1, 2N, 1, 1)
p_n = self._get_p_n(N, dtype)
# (1, 2N, h, w)
p_0 = self._get_p_0(h, w, N, dtype)
p = p_0 + p_n + offset
return p
def _get_x_q(self, x, q, N):
b, h, w, _ = q.size()
padded_w = x.size(3)
c = x.size(1)
# (b, c, h*w)
x = x.contiguous().view(b, c, -1)
# (b, h, w, N)
index = q[..., :N] * padded_w + q[..., N:] # offset_x*w + offset_y
# (b, c, h*w*N)
index = index.contiguous().unsqueeze(dim=1).expand(-1, c, -1, -1, -1).contiguous().view(b, c, -1)
x_offset = x.gather(dim=-1, index=index).contiguous().view(b, c, h, w, N)
return x_offset
# Stacking resampled features in the row direction.
@staticmethod
def _reshape_x_offset(x_offset, num_param):
b, c, h, w, n = x_offset.size()
x_offset = rearrange(x_offset, 'b c h w n -> b c (h n) w')
return x_offset
2. 将YOLOv9工程中models下yolo.py文件中700行（可能因为版本改变，新建一个elif分支即可）左右的位置加入下方代码代码。
elif m in (AKConv,):
c1 = ch[f]
args.insert(0, c1)
3.3 运行配置文件
# YOLOv9
# Powered bu https://blog.csdn.net/StopAndGoyyy
# 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, [256, 128, 64, 1]], # 3
# avg-conv down
[-1, 1, ADown, [256]], # 4-P3/8
# elan-2 block
[-1, 1, RepNCSPELAN4, [512, 256, 128, 1]], # 5
# avg-conv down
[-1, 1, ADown, [512]], # 6-P4/16
# elan-2 block
[-1, 1, RepNCSPELAN4, [512, 512, 256, 1]], # 7
# avg-conv down
[-1, 1, ADown, [512]], # 8-P5/32
# elan-2 block
[-1, 1, RepNCSPELAN4, [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, [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, [256, 256, 128, 1]], # 16 (P3/8-small)
# avg-conv-down merge
[-1, 1, ADown, [256]],
[[-1, 13], 1, Concat, [1]], # cat head P4
# elan-2 block
[-1, 1, RepNCSPELAN4, [512, 512, 256, 1]], # 19 (P4/16-medium)
# avg-conv-down merge
[-1, 1, ADown, [512]],
[[-1, 10], 1, Concat, [1]], # cat head P5
# elan-2 block
[-1, 1, RepNCSPELAN4, [512, 512, 256, 1]], # 22 (P5/32-large)
# multi-level reversible auxiliary branch
# 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, [256, 128, 64, 1]], # 28
# avg-conv down fuse
[-1, 1, ADown, [256]], # 29-P3/8
[[23, 24, 25, -1], 1, CBFuse, [[0, 0, 0]]], # 30
# elan-2 block
[-1, 1, RepNCSPELAN4, [512, 256, 128, 1]], # 31
# avg-conv down fuse
[-1, 1, ADown, [512]], # 32-P4/16
[[24, 25, -1], 1, CBFuse, [[1, 1]]], # 33
# elan-2 block
[-1, 1, RepNCSPELAN4, [512, 512, 256, 1]], # 34
# avg-conv down fuse
[-1, 1, ADown, [512]], # 35-P5/32
[[25, -1], 1, CBFuse, [[2]]], # 36
# elan-2 block
[-1, 1, RepNCSPELAN4, [512, 512, 256, 1]], # 37
[-1, 1, AKConv, [512]], # 38
# detection head
# detect
[[31, 34, 38, 16, 19, 22], 1, DualDDetect, [nc]], # DualDDetect(A3, A4, A5, P3, P4, P5)
]
3.4 训练过程
