一、导言
介绍了一种名为AKConv（Alterable Kernel Convolution）的新型卷积操作，旨在解决标准卷积操作存在的两个根本性问题。首先，标准卷积操作受限于局部窗口，无法捕获来自其他位置的信息，且其采样形状固定；其次，卷积核的大小固定为k×k的正方形，参数数量随着尺寸的增加呈平方增长，这在硬件资源上不够友好。
AKConv的关键创新点在于它能够提供任意数量的参数和任意采样形状，从而为网络性能与开销之间的权衡提供了更丰富的选择。通过一种新的坐标生成算法定义了任意大小卷积核的初始位置，并引入偏移量来适应不同位置目标的变化，使卷积核能够灵活地适应目标形态。实验结果显示，AKConv在保持或提升模型检测性能的同时，能有效减少参数数量和计算负担，特别是在处理非规则样本形状时表现出了优势。
优点：
- 灵活性与适应性： AKConv允许卷积核具有任意数量的参数和多种形状，这提高了网络对不同数据集和目标变化的适应能力。
- 参数效率： AKConv的参数数量随卷积核尺寸的增大呈线性增长，相比标准卷积和可变形卷积的平方增长更为硬件友好。
- 性能提升： 在COCO2017、VOC 7+ 12等基准数据集上的实验表明，使用AKConv替换标准卷积可以维持甚至提高目标检测性能，尤其是在较小的卷积核尺寸下减少了计算负担。
- 设计创新： AKConv通过学习偏移量动态调整采样形状，克服了传统卷积和可变形卷积在形状和尺寸上的局限性。
缺点：
- 实现复杂度： 实现AKConv需要设计新的坐标生成算法和偏移量学习机制，这可能增加了模型实现的复杂度。
- 训练难度： 由于AKConv具有更多自由度，可能会增加模型训练的难度，如优化问题的复杂性和收敛速度。
- 泛化能力考量： 文章没有充分探讨AKConv在未见过的数据或极端条件下的泛化性能，这可能影响其在实际应用中的可靠性。
- 公平性比较限制： 实验中为了公平比较，AKConv也采用了零填充，但这一调整可能掩盖了AKConv本身特性的一些潜在优势或劣势。
综上所述，AKConv提出了一种新的卷积方式，旨在提升卷积神经网络的灵活性和效率，尤其是在处理非规则目标和减小模型复杂性方面展现出了潜力，但同时也带来了实施和训练上的挑战。
二、准备工作
首先在YOLOv5/v7的models文件夹下新建文件akconv.py，导入如下代码
from models.common import *
from einops import rearrange
class AKConv(nn.Module):
def __init__(self, inc, outc, num_param=5, stride=1, bias=None):
super(AKConv, self).__init__()
self.num_param = num_param
self.stride = stride
self.conv = nn.Sequential(nn.Conv2d(inc, outc, kernel_size=(num_param, 1), stride=(num_param, 1), bias=bias),
nn.BatchNorm2d(outc),
nn.SiLU()) # the conv adds the BN and SiLU to compare original Conv in YOLOv5.
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))
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))
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))
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()
# using Conv3d
# x_offset = x_offset.permute(0,1,4,2,3), then Conv3d(c,c_out, kernel_size =(num_param,1,1),stride=(num_param,1,1),bias= False)
# using 1 × 1 Conv
# x_offset = x_offset.permute(0,1,4,2,3), then, x_offset.view(b,c×num_param,h,w) finally, Conv2d(c×num_param,c_out, kernel_size =1,stride=1,bias= False)
# using the column conv as follow， then, Conv2d(inc, outc, kernel_size=(num_param, 1), stride=(num_param, 1), bias=bias)
x_offset = rearrange(x_offset, 'b c h w n -> b c (h n) w')
return x_offset其次在在YOLOv5/v7项目文件下的models/yolo.py中在文件首部添加代码
from models.akconv import AKConv并搜索def parse_model(d, ch)
定位到如下行添加以下代码
AKConv,
三、YOLOv7-tiny改进工作
完成二后，在YOLOv7项目文件下的models文件夹下创建新的文件yolov7-tiny-akconv.yaml，导入如下代码。
# parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# yolov7-tiny backbone
backbone:
# [from, number, module, args] c2, k=1, s=1, p=None, g=1, act=True
[[-1, 1, Conv, [32, 3, 2, None, 1, nn.LeakyReLU(0.1)]], # 0-P1/2
[-1, 1, Conv, [64, 3, 2, None, 1, nn.LeakyReLU(0.1)]], # 1-P2/4
[-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[[-1, -2, -3, -4], 1, Concat, [1]],
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 7
[-1, 1, MP, []], # 8-P3/8
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[[-1, -2, -3, -4], 1, Concat, [1]],
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 14
[-1, 1, MP, []], # 15-P4/16
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[[-1, -2, -3, -4], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 21
[-1, 1, MP, []], # 22-P5/32
[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[[-1, -2, -3, -4], 1, Concat, [1]],
[-1, 1, Conv, [512, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 28
]
# yolov7-tiny head
head:
[[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, SP, [5]],
[-2, 1, SP, [9]],
[-3, 1, SP, [13]],
[[-1, -2, -3, -4], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[[-1, -7], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 37
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[21, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P4
[[-1, -2], 1, Concat, [1]],
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[[-1, -2, -3, -4], 1, Concat, [1]],
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 47
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[14, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P3
[[-1, -2], 1, Concat, [1]],
[-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[[-1, -2, -3, -4], 1, Concat, [1]],
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 57
[-1, 1, Conv, [128, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
[[-1, 47], 1, Concat, [1]],
[-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[[-1, -2, -3, -4], 1, Concat, [1]],
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # 65
[-1, 1, Conv, [256, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
[[-1, 37], 1, Concat, [1]],
[-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[[-1, -2, -3, -4], 1, Concat, [1]],
[-1, 1, AKConv, [256, 1, 1]], # 73
[57, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[65, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[73, 1, Conv, [512, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
[[74,75,76], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5)
]
from n params module arguments
0 -1 1 928 models.common.Conv [3, 32, 3, 2, None, 1, LeakyReLU(negative_slope=0.1)]
1 -1 1 18560 models.common.Conv [32, 64, 3, 2, None, 1, LeakyReLU(negative_slope=0.1)]
2 -1 1 2112 models.common.Conv [64, 32, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
3 -2 1 2112 models.common.Conv [64, 32, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
4 -1 1 9280 models.common.Conv [32, 32, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
5 -1 1 9280 models.common.Conv [32, 32, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
6 [-1, -2, -3, -4] 1 0 models.common.Concat [1]
7 -1 1 8320 models.common.Conv [128, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
8 -1 1 0 models.common.MP []
9 -1 1 4224 models.common.Conv [64, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
10 -2 1 4224 models.common.Conv [64, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
11 -1 1 36992 models.common.Conv [64, 64, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
12 -1 1 36992 models.common.Conv [64, 64, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
13 [-1, -2, -3, -4] 1 0 models.common.Concat [1]
14 -1 1 33024 models.common.Conv [256, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
15 -1 1 0 models.common.MP []
16 -1 1 16640 models.common.Conv [128, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
17 -2 1 16640 models.common.Conv [128, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
18 -1 1 147712 models.common.Conv [128, 128, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
19 -1 1 147712 models.common.Conv [128, 128, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
20 [-1, -2, -3, -4] 1 0 models.common.Concat [1]
21 -1 1 131584 models.common.Conv [512, 256, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
22 -1 1 0 models.common.MP []
23 -1 1 66048 models.common.Conv [256, 256, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
24 -2 1 66048 models.common.Conv [256, 256, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
25 -1 1 590336 models.common.Conv [256, 256, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
26 -1 1 590336 models.common.Conv [256, 256, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
27 [-1, -2, -3, -4] 1 0 models.common.Concat [1]
28 -1 1 525312 models.common.Conv [1024, 512, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
29 -1 1 131584 models.common.Conv [512, 256, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
30 -2 1 131584 models.common.Conv [512, 256, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
31 -1 1 0 models.common.SP [5]
32 -2 1 0 models.common.SP [9]
33 -3 1 0 models.common.SP [13]
34 [-1, -2, -3, -4] 1 0 models.common.Concat [1]
35 -1 1 262656 models.common.Conv [1024, 256, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
36 [-1, -7] 1 0 models.common.Concat [1]
37 -1 1 131584 models.common.Conv [512, 256, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
38 -1 1 33024 models.common.Conv [256, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
39 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
40 21 1 33024 models.common.Conv [256, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
41 [-1, -2] 1 0 models.common.Concat [1]
42 -1 1 16512 models.common.Conv [256, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
43 -2 1 16512 models.common.Conv [256, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
44 -1 1 36992 models.common.Conv [64, 64, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
45 -1 1 36992 models.common.Conv [64, 64, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
46 [-1, -2, -3, -4] 1 0 models.common.Concat [1]
47 -1 1 33024 models.common.Conv [256, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
48 -1 1 8320 models.common.Conv [128, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
49 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
50 14 1 8320 models.common.Conv [128, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
51 [-1, -2] 1 0 models.common.Concat [1]
52 -1 1 4160 models.common.Conv [128, 32, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
53 -2 1 4160 models.common.Conv [128, 32, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
54 -1 1 9280 models.common.Conv [32, 32, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
55 -1 1 9280 models.common.Conv [32, 32, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
56 [-1, -2, -3, -4] 1 0 models.common.Concat [1]
57 -1 1 8320 models.common.Conv [128, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
58 -1 1 73984 models.common.Conv [64, 128, 3, 2, None, 1, LeakyReLU(negative_slope=0.1)]
59 [-1, 47] 1 0 models.common.Concat [1]
60 -1 1 16512 models.common.Conv [256, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
61 -2 1 16512 models.common.Conv [256, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
62 -1 1 36992 models.common.Conv [64, 64, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
63 -1 1 36992 models.common.Conv [64, 64, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
64 [-1, -2, -3, -4] 1 0 models.common.Concat [1]
65 -1 1 33024 models.common.Conv [256, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
66 -1 1 295424 models.common.Conv [128, 256, 3, 2, None, 1, LeakyReLU(negative_slope=0.1)]
67 [-1, 37] 1 0 models.common.Concat [1]
68 -1 1 65792 models.common.Conv [512, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
69 -2 1 65792 models.common.Conv [512, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
70 -1 1 147712 models.common.Conv [128, 128, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
71 -1 1 147712 models.common.Conv [128, 128, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
72 [-1, -2, -3, -4] 1 0 models.common.Concat [1]
73 -1 1 140802 models.akconv.AKConv [512, 256, 1, 1]
74 57 1 73984 models.common.Conv [64, 128, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
75 65 1 295424 models.common.Conv [128, 256, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
76 73 1 1180672 models.common.Conv [256, 512, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
77 [74, 75, 76] 1 17132 models.yolo.IDetect [1, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
Model Summary: 265 layers, 6024206 parameters, 6024206 gradients, 13.2 GFLOPS运行后若打印出如上文本代表改进成功。
四、YOLOv5s改进工作
完成二后，在YOLOv5项目文件下的models文件夹下创建新的文件yolov5s-akconv.yaml，导入如下代码。
# Parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 6, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 3, C3, [1024]],
[-1, 1, SPPF, [1024, 5]], # 9
]
# YOLOv5 v6.0 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, AKConv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
from n params module arguments
0 -1 1 3520 models.common.Conv [3, 32, 6, 2, 2]
1 -1 1 18560 models.common.Conv [32, 64, 3, 2]
2 -1 1 18816 models.common.C3 [64, 64, 1]
3 -1 1 73984 models.common.Conv [64, 128, 3, 2]
4 -1 2 115712 models.common.C3 [128, 128, 2]
5 -1 1 295424 models.common.Conv [128, 256, 3, 2]
6 -1 3 625152 models.common.C3 [256, 256, 3]
7 -1 1 1180672 models.common.Conv [256, 512, 3, 2]
8 -1 1 1182720 models.common.C3 [512, 512, 1]
9 -1 1 656896 models.common.SPPF [512, 512, 5]
10 -1 1 131584 models.common.Conv [512, 256, 1, 1]
11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
12 [-1, 6] 1 0 models.common.Concat [1]
13 -1 1 361984 models.common.C3 [512, 256, 1, False]
14 -1 1 33024 models.common.Conv [256, 128, 1, 1]
15 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
16 [-1, 4] 1 0 models.common.Concat [1]
17 -1 1 90880 models.common.C3 [256, 128, 1, False]
18 -1 1 147712 models.common.Conv [128, 128, 3, 2]
19 [-1, 14] 1 0 models.common.Concat [1]
20 -1 1 296448 models.common.C3 [256, 256, 1, False]
21 -1 1 210950 models.akconv.AKConv [256, 256, 3, 2]
22 [-1, 10] 1 0 models.common.Concat [1]
23 -1 1 1182720 models.common.C3 [512, 512, 1, False]
24 [17, 20, 23] 1 16182 models.yolo.Detect [1, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
Model Summary: 272 layers, 6642940 parameters, 6642940 gradients, 15.6 GFLOPs运行后若打印出如上文本代表改进成功。
五、YOLOv5n改进工作
完成二后，在YOLOv5项目文件下的models文件夹下创建新的文件yolov5n-akconv.yaml，导入如下代码。
# Parameters
nc: 80 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.25 # layer channel multiple
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 6, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 3, C3, [1024]],
[-1, 1, SPPF, [1024, 5]], # 9
]
# YOLOv5 v6.0 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, AKConv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]
from n params module arguments
0 -1 1 1760 models.common.Conv [3, 16, 6, 2, 2]
1 -1 1 4672 models.common.Conv [16, 32, 3, 2]
2 -1 1 4800 models.common.C3 [32, 32, 1]
3 -1 1 18560 models.common.Conv [32, 64, 3, 2]
4 -1 2 29184 models.common.C3 [64, 64, 2]
5 -1 1 73984 models.common.Conv [64, 128, 3, 2]
6 -1 3 156928 models.common.C3 [128, 128, 3]
7 -1 1 295424 models.common.Conv [128, 256, 3, 2]
8 -1 1 296448 models.common.C3 [256, 256, 1]
9 -1 1 164608 models.common.SPPF [256, 256, 5]
10 -1 1 33024 models.common.Conv [256, 128, 1, 1]
11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
12 [-1, 6] 1 0 models.common.Concat [1]
13 -1 1 90880 models.common.C3 [256, 128, 1, False]
14 -1 1 8320 models.common.Conv [128, 64, 1, 1]
15 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
16 [-1, 4] 1 0 models.common.Concat [1]
17 -1 1 22912 models.common.C3 [128, 64, 1, False]
18 -1 1 36992 models.common.Conv [64, 64, 3, 2]
19 [-1, 14] 1 0 models.common.Concat [1]
20 -1 1 74496 models.common.C3 [128, 128, 1, False]
21 -1 1 56326 models.akconv.AKConv [128, 128, 3, 2]
22 [-1, 10] 1 0 models.common.Concat [1]
23 -1 1 296448 models.common.C3 [256, 256, 1, False]
24 [17, 20, 23] 1 8118 models.yolo.Detect [1, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [64, 128, 256]]
Model Summary: 272 layers, 1673884 parameters, 1673884 gradients, 4.2 GFLOPs运行后打印如上代码说明改进成功。
更多文章产出中，主打简洁和准确，欢迎关注我，共同探讨！
