YOLOv11融合可变核卷积AKConv模块及相关改进思路|YOLO改进最简教程

---

YOLOv11v10v8使用教程：  YOLOv11入门到入土使用教程

YOLOv11改进汇总贴：YOLOv11及自研模型更新汇总 

---

《AKConv: Convolutional Kernel with Arbitrary Sampled Shapes and Arbitrary Number of Parameters》

一、 模块介绍

        论文链接：https://arxiv.org/pdf/2311.11587v2

        代码链接：https://github.com/CV-ZhangXin/AKConv

论文速览：基于卷积运算的神经网络在深度学习领域取得了显著的成果，但标准卷积运算存在两个固有缺陷。一方面，卷积操作局限于本地窗口，无法从其他位置捕获信息，其采样形状是固定的。另一方面，卷积核的大小固定为 k × k，这是一个固定的方形，参数的数量往往随着大小而呈方形增长。很明显，目标的形状和大小在不同的数据集和不同的位置是不同的。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。针对上述问题，本研究探讨了可更改内核卷积 （AKConv），它为卷积内核提供了任意数量的参数和任意采样形状，为网络开销和性能之间的权衡提供了更丰富的选择。在 AKConv 中，通过新的坐标生成算法为任意大小的卷积核定义初始位置。为了适应目标的变化，引入了偏移量来调整每个位置的样本形状。此外，通过使用具有相同大小和不同初始采样形状的 AKConv 来探索神经网络的效果。AKConv 完成了通过不规则卷积运算进行高效特征提取的过程，为卷积采样形状带来了更多的探索选择。在代表性数据集 COCO2017、VOC 7+12 和 VisDrone-DET2021 上的目标检测实验充分展示了 AKConv 的优势。AKConv 可以作为即插即用的卷积运算来代替卷积运算，从而提高网络性能。

总结：一种可变核的卷积模块，单独用效果一般，组合模块效果可以。​

---

二、 加入到YOLO中

2.1 创建脚本文件

        首先在ultralytics->nn路径下创建blocks.py脚本，用于存放模块代码。

2.2 复制代码        

        复制代码粘到刚刚创建的blocks.py脚本中，如下图所示：

import torch
import torch.nn as nn
import torch.nn.functional as F
import math
from ultralytics.nn.modules.conv import Conv
from einops import rearrange


class AKConv(nn.Module):
    def __init__(self, inc, outc, stride=1, num_param=5, 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))
        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

2.3 更改task.py文件 

       打开ultralytics->nn->modules->task.py，在脚本空白处导入函数。

from ultralytics.nn.blocks import *

        之后找到模型解析函数parse_model（约在tasks.py脚本中940行左右位置，可能因代码版本不同变动），在该函数的最后一个else分支上面增加相关解析代码。

        elif m is AKConv:
            c2 = args[0]
            args = [ch[f], *args]

2.4 更改yaml文件 

yam文件解读：YOLO系列 “.yaml“文件解读_yolo yaml文件-CSDN博客

       打开更改ultralytics/cfg/models/11路径下的YOLOv11.yaml文件，替换原有模块。（放在该位置仅能插入该模块，具体效果未知。博主精力有限，仅完成与其他模块二次创新融合的测试，结构图见文末，代码见群文件更新。）

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect

# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n.yaml' will call yolo11.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs

# YOLO11n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, AKConv, [512]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]] # 9
  - [-1, 2, C2PSA, [1024]] # 10

# YOLO11n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, False]] # 13

  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)

  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

---

 2.5 修改train.py文件

       创建Train脚本用于训练。

from ultralytics.models import YOLO
import os
os.environ['KMP_DUPLICATE_LIB_OK'] = 'True'

if __name__ == '__main__':
    model = YOLO(model='ultralytics/cfg/models/11/yolo11.yaml')
    # model.load('yolov8n.pt')
    model.train(data='./data.yaml', epochs=2, batch=1, device='0', imgsz=640, workers=2, cache=False,
                amp=True, mosaic=False, project='runs/train', name='exp')

         在train.py脚本中填入修改好的yaml路径，运行即可训练，数据集创建教程见下方链接。

YOLOv11入门到入土使用教程(含结构图)_yolov11使用教程-CSDN博客

三、相关改进思路（2024/11/8日群文件）

根据AKconv模块特性，可替换C2f、C3模块中的BottleNeck中的卷积部分，代码见群文件，结构如图。

 ⭐另外，融合上百种深度学习改进模块的YOLO项目仅119（含百种改进的v9），RTDETR119,含高性能自研模型，更易发论文，代码每周更新，欢迎点击下方小卡片加我了解。⭐

---