大感受野的小波卷积WTConv助力YOLOv11

原创已于 2024-11-22 15:16:52 修改 · 1.8k 阅读

49 ·

CC 4.0 BY-SA版权

文章标签：

#YOLO

于 2024-10-28 18:26:24 首次发布

yolo改进专栏收录该内容

2 篇文章

订阅专栏

一、本文介绍

WTConv（小波卷积层），它利用小波变换（WT）来解决卷积神经网络（CNN）在实现大感受野时遇到的过度参数化问题。WTConv的主要目的是通过对输入数据的不同频率带进行处理，使CNN能够更有效地捕捉局部和全局特征，WTConv成功解决了CNN在感受野扩展中的参数膨胀问题，提供了一种更为高效、鲁棒且易于集成的卷积层解决方案，我将其用于二次创新YOLOv11中的C3k2机制可以减少一定参数量和计算量，达到一个可观的轻量化作用（这种小波Conv对于目前的创新角度来说是非常流行的）。

二、原理介绍

https://arxiv.org/pdf/2407.05848 WTConv/wtconv/util/wavelet.py at main · BGU-CS-VIL/WTConv · GitHub

三、核心代码

import torch.nn as nn
from functools import partial
import pywt
import pywt.data
import torch
import torch.nn.functional as F
 
 
def create_wavelet_filter(wave, in_size, out_size, type=torch.float):
    w = pywt.Wavelet(wave)
    dec_hi = torch.tensor(w.dec_hi[::-1], dtype=type)
    dec_lo = torch.tensor(w.dec_lo[::-1], dtype=type)
    dec_filters = torch.stack([dec_lo.unsqueeze(0) * dec_lo.unsqueeze(1),
                               dec_lo.unsqueeze(0) * dec_hi.unsqueeze(1),
                               dec_hi.unsqueeze(0) * dec_lo.unsqueeze(1),
                               dec_hi.unsqueeze(0) * dec_hi.unsqueeze(1)], dim=0)
 
    dec_filters = dec_filters[:, None].repeat(in_size, 1, 1, 1)
 
    rec_hi = torch.tensor(w.rec_hi[::-1], dtype=type).flip(dims=[0])
    rec_lo = torch.tensor(w.rec_lo[::-1], dtype=type).flip(dims=[0])
    rec_filters = torch.stack([rec_lo.unsqueeze(0) * rec_lo.unsqueeze(1),
                               rec_lo.unsqueeze(0) * rec_hi.unsqueeze(1),
                               rec_hi.unsqueeze(0) * rec_lo.unsqueeze(1),
                               rec_hi.unsqueeze(0) * rec_hi.unsqueeze(1)], dim=0)
 
    rec_filters = rec_filters[:, None].repeat(out_size, 1, 1, 1)
 
    return dec_filters, rec_filters
 
def wavelet_transform(x, filters):
    b, c, h, w = x.shape
    pad = (filters.shape[2] // 2 - 1, filters.shape[3] // 2 - 1)
    x = F.conv2d(x, filters, stride=2, groups=c, padding=pad)
    x = x.reshape(b, c, 4, h // 2, w // 2)
    return x
 
 
def inverse_wavelet_transform(x, filters):
    b, c, _, h_half, w_half = x.shape
    pad = (filters.shape[2] // 2 - 1, filters.shape[3] // 2 - 1)
    x = x.reshape(b, c * 4, h_half, w_half)
    x = F.conv_transpose2d(x, filters, stride=2, groups=c, padding=pad)
    return x
 
 
class WTConv2d(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size=5, stride=1, bias=True, wt_levels=1, wt_type='db1'):
        super(WTConv2d, self).__init__()
 
        assert in_channels == out_channels
 
        self.in_channels = in_channels
        self.wt_levels = wt_levels
        self.stride = stride
        self.dilation = 1
 
        self.wt_filter, self.iwt_filter = create_wavelet_filter(wt_type, in_channels, in_channels, torch.float)
        self.wt_filter = nn.Parameter(self.wt_filter, requires_grad=False)
        self.iwt_filter = nn.Parameter(self.iwt_filter, requires_grad=False)
 
        self.wt_function = partial(wavelet_transform, filters=self.wt_filter)
        self.iwt_function = partial(inverse_wavelet_transform, filters=self.iwt_filter)
 
        self.base_conv = nn.Conv2d(in_channels, in_channels, kernel_size, padding='same', stride=1, dilation=1,
                                   groups=in_channels, bias=bias)
        self.base_scale = _ScaleModule([1, in_channels, 1, 1])
 
        self.wavelet_convs = nn.ModuleList(
            [nn.Conv2d(in_channels * 4, in_channels * 4, kernel_size, padding='same', stride=1, dilation=1,
                       groups=in_channels * 4, bias=False) for _ in range(self.wt_levels)]
        )
        self.wavelet_scale = nn.ModuleList(
            [_ScaleModule([1, in_channels * 4, 1, 1], init_scale=0.1) for _ in range(self.wt_levels)]
        )
 
        if self.stride > 1:
            self.stride_filter = nn.Parameter(torch.ones(in_channels, 1, 1, 1), requires_grad=False)
            self.do_stride = lambda x_in: F.conv2d(x_in, self.stride_filter, bias=None, stride=self.stride,
                                                   groups=in_channels)
        else:
            self.do_stride = None
 
    def forward(self, x):
 
        x_ll_in_levels = []
        x_h_in_levels = []
        shapes_in_levels = []
 
        curr_x_ll = x
 
        for i in range(self.wt_levels):
            curr_shape = curr_x_ll.shape
            shapes_in_levels.append(curr_shape)
            if (curr_shape[2] % 2 > 0) or (curr_shape[3] % 2 > 0):
                curr_pads = (0, curr_shape[3] % 2, 0, curr_shape[2] % 2)
                curr_x_ll = F.pad(curr_x_ll, curr_pads)
 
            curr_x = self.wt_function(curr_x_ll)
            curr_x_ll = curr_x[:, :, 0, :, :]
 
            shape_x = curr_x.shape
            curr_x_tag = curr_x.reshape(shape_x[0], shape_x[1] * 4, shape_x[3], shape_x[4])
            curr_x_tag = self.wavelet_scale[i](self.wavelet_convs[i](curr_x_tag))
            curr_x_tag = curr_x_tag.reshape(shape_x)
 
            x_ll_in_levels.append(curr_x_tag[:, :, 0, :, :])
            x_h_in_levels.append(curr_x_tag[:, :, 1:4, :, :])
 
        next_x_ll = 0
 
        for i in range(self.wt_levels - 1, -1, -1):
            curr_x_ll = x_ll_in_levels.pop()
            curr_x_h = x_h_in_levels.pop()
            curr_shape = shapes_in_levels.pop()
 
            curr_x_ll = curr_x_ll + next_x_ll
 
            curr_x = torch.cat([curr_x_ll.unsqueeze(2), curr_x_h], dim=2)
            next_x_ll = self.iwt_function(curr_x)
 
            next_x_ll = next_x_ll[:, :, :curr_shape[2], :curr_shape[3]]
 
        x_tag = next_x_ll
        assert len(x_ll_in_levels) == 0
 
        x = self.base_scale(self.base_conv(x))
        x = x + x_tag
 
        if self.do_stride is not None:
            x = self.do_stride(x)
 
        return x
 
 
class _ScaleModule(nn.Module):
    def __init__(self, dims, init_scale=1.0, init_bias=0):
        super(_ScaleModule, self).__init__()
        self.dims = dims
        self.weight = nn.Parameter(torch.ones(*dims) * init_scale)
        self.bias = None
 
    def forward(self, x):
        return torch.mul(self.weight, x)
 
 
 
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):
        """Initialize Conv layer with given arguments including activation."""
        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):
        """Apply convolution, batch normalization and activation to input tensor."""
        return self.act(self.bn(self.conv(x)))
 
    def forward_fuse(self, x):
        """Perform transposed convolution of 2D data."""
        return self.act(self.conv(x))
 
 
class Bottleneck(nn.Module):
    """Standard bottleneck."""
 
    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
        """Initializes a bottleneck module with given input/output channels, shortcut option, group, kernels, and
        expansion.
        """
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, k[0], 1)
        if c_ == c2:
            self.cv2 = WTConv2d(c_, c2, 5, 1)
        else:
            self.cv2 = Conv(c_, c2, k[1], 1, g=g)
        self.add = shortcut and c1 == c2
 
    def forward(self, x):
        """'forward()' applies the YOLO FPN to input data."""
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
 
 
class C2f(nn.Module):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""
 
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
        """Initializes a CSP bottleneck with 2 convolutions and n Bottleneck blocks for faster processing."""
        super().__init__()
        self.c = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv((2 + n) * self.c, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))
 
    def forward(self, x):
        """Forward pass through C2f layer."""
        y = list(self.cv1(x).chunk(2, 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))
 
    def forward_split(self, x):
        """Forward pass using split() instead of chunk()."""
        y = list(self.cv1(x).split((self.c, self.c), 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))
 
class C3(nn.Module):
    """CSP Bottleneck with 3 convolutions."""
 
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        """Initialize the CSP Bottleneck with given channels, number, shortcut, groups, and expansion values."""
        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(*(Bottleneck(c_, c_, shortcut, g, k=((1, 1), (3, 3)), e=1.0) for _ in range(n)))
 
    def forward(self, x):
        """Forward pass through the CSP bottleneck with 2 convolutions."""
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
 
class C3k(C3):
    """C3k is a CSP bottleneck module with customizable kernel sizes for feature extraction in neural networks."""
 
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, k=3):
        """Initializes the C3k module with specified channels, number of layers, and configurations."""
        super().__init__(c1, c2, n, shortcut, g, e)
        c_ = int(c2 * e)  # hidden channels
        # self.m = nn.Sequential(*(RepBottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, k=(k, k), e=1.0) for _ in range(n)))
 
class C3k2_WTConv(C2f):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""
 
    def __init__(self, c1, c2, n=1, c3k=False, e=0.5, g=1, shortcut=True):
        """Initializes the C3k2 module, a faster CSP Bottleneck with 2 convolutions and optional C3k blocks."""
        super().__init__(c1, c2, n, shortcut, g, e)
        self.m = nn.ModuleList(
            C3k(self.c, self.c, 2, shortcut, g) if c3k else Bottleneck(self.c, self.c, shortcut, g) for _ in range(n)
        )
 
 
 
if __name__ == "__main__":
    # Generating Sample image
    image_size = (1, 64, 240, 240)
    image = torch.rand(*image_size)
 
    # Model
    mobilenet_v1 = C3k2_WTConv(64, 64)
 
    out = mobilenet_v1(image)
    print(out.size())

四、手把手教你添加C3k2
4.1 修改一
第一还是建立文件，我们找到如下ultralytics/nn/modules文件夹下建立一个目录名字呢就是'Addmodules'文件夹(用群内的文件的话已经有了无需新建)！然后在其内部建立一个新的py文件将核心代码复制粘贴进去即可。

4.2 修改二

第二步我们在该目录下创建一个新的py文件名字为'__init__.py'(用群内的文件的话已经有了无需新建)，然后在其内部导入我们的检测头如下图所示。

4.3 修改三

第三步我门中到如下文件'ultralytics/nn/tasks.py'进行导入和注册我们的模块(用群内的文件的话已经有了无需重新导入直接开始第四步即可)！

4.4 修改四

按照我的添加在parse_model里添加即可。

5 yaml文件

# 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_WTConv, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2_WTConv, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2_WTConv, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2_WTConv, [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_WTConv, [512, False]] # 13
 
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2_WTConv, [256, False]] # 16 (P3/8-small)
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2_WTConv, [512, False]] # 19 (P4/16-medium)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2_WTConv, [1024, True]] # 22 (P5/32-large)
 
  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)