1. 文章主要内容
本篇博客主要涉及轻量化多维动态卷积ODConv，融合到YOLOv5模型中，减少计算量的同时保持精度稳定或略微上涨。（通读本篇博客需要7分钟左右的时间）。
2. 介绍
ODconv沿着空间、输入通道、输出通道以及卷积核空间的核维度学习更丰富的注意力，且采用更少的卷积核，使其在取得更优性能的同时也能降低计算量。
3. 详细代码改进流程
3.1 ODconv源代码
源代码如下：
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.autograd
class ODConv(nn.Sequential):
def __init__(self, in_planes, out_planes, kernel_size=3, stride=1, groups=1, norm_layer=nn.BatchNorm2d,
reduction=0.0625, kernel_num=1):
padding = (kernel_size - 1) // 2
super(ODConv, self).__init__(
ODConv2d(in_planes, out_planes, kernel_size, stride, padding, groups=groups,
reduction=reduction, kernel_num=kernel_num),
norm_layer(out_planes),
nn.SiLU()
)
class Attention(nn.Module):
def __init__(self, in_planes, out_planes, kernel_size,
groups=1,
reduction=0.0625,
kernel_num=4,
min_channel=16):
super(Attention, self).__init__()
attention_channel = max(int(in_planes * reduction), min_channel)
self.kernel_size = kernel_size
self.kernel_num = kernel_num
self.temperature = 1.0
self.avgpool = nn.AdaptiveAvgPool2d(1)
self.fc = nn.Conv2d(in_planes, attention_channel, 1, bias=False)
self.bn = nn.BatchNorm2d(attention_channel)
self.relu = nn.ReLU(inplace=True)
self.channel_fc = nn.Conv2d(attention_channel, in_planes, 1, bias=True)
self.func_channel = self.get_channel_attention
if in_planes == groups and in_planes == out_planes: # depth-wise convolution
self.func_filter = self.skip
else:
self.filter_fc = nn.Conv2d(attention_channel, out_planes, 1, bias=True)
self.func_filter = self.get_filter_attention
if kernel_size == 1: # point-wise convolution
self.func_spatial = self.skip
else:
self.spatial_fc = nn.Conv2d(attention_channel, kernel_size * kernel_size, 1, bias=True)
self.func_spatial = self.get_spatial_attention
if kernel_num == 1:
self.func_kernel = self.skip
else:
self.kernel_fc = nn.Conv2d(attention_channel, kernel_num, 1, bias=True)
self.func_kernel = self.get_kernel_attention
self.bn_1 = nn.LayerNorm([attention_channel,1,1])
self._initialize_weights()
def _initialize_weights(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
if m.bias is not None:
nn.init.constant_(m.bias, 0)
if isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def update_temperature(self, temperature):
self.temperature = temperature
@staticmethod
def skip(_):
return 1.0
def get_channel_attention(self, x):
channel_attention = torch.sigmoid(self.channel_fc(x).view(x.size(0), -1, 1, 1) / self.temperature)
return channel_attention
def get_filter_attention(self, x):
filter_attention = torch.sigmoid(self.filter_fc(x).view(x.size(0), -1, 1, 1) / self.temperature)
return filter_attention
def get_spatial_attention(self, x):
spatial_attention = self.spatial_fc(x).view(x.size(0), 1, 1, 1, self.kernel_size, self.kernel_size)
spatial_attention = torch.sigmoid(spatial_attention / self.temperature)
return spatial_attention
def get_kernel_attention(self, x):
kernel_attention = self.kernel_fc(x).view(x.size(0), -1, 1, 1, 1, 1)
kernel_attention = F.softmax(kernel_attention / self.temperature, dim=1)
return kernel_attention
def forward(self, x):
x = self.avgpool(x)
x = self.fc(x)
x = self.bn_1(x)
x = self.relu(x)
return self.func_channel(x), self.func_filter(x), self.func_spatial(x), self.func_kernel(x)
class ODConv2d(nn.Module):
def __init__(self,
in_planes,
out_planes,
kernel_size=3,
stride=1,
padding=0,
dilation=1,
groups=1,
reduction=0.0625,
kernel_num=1):
super(ODConv2d, self).__init__()
self.in_planes = in_planes
self.out_planes = out_planes
self.kernel_size = kernel_size
self.stride = stride
self.padding = padding
self.dilation = dilation
self.groups = groups
self.kernel_num = kernel_num
self.attention = Attention(in_planes, out_planes, kernel_size, groups=groups,
reduction=reduction, kernel_num=kernel_num)
self.weight = nn.Parameter(torch.randn(kernel_num, out_planes, in_planes//groups, kernel_size, kernel_size),
requires_grad=True)
self._initialize_weights()
if self.kernel_size == 1 and self.kernel_num == 1:
self._forward_impl = self._forward_impl_pw1x
else:
self._forward_impl = self._forward_impl_common
def _initialize_weights(self):
for i in range(self.kernel_num):
nn.init.kaiming_normal_(self.weight[i], mode='fan_out', nonlinearity='relu')
def update_temperature(self, temperature):
self.attention.update_temperature(temperature)
def _forward_impl_common(self, x):
channel_attention, filter_attention, spatial_attention, kernel_attention = self.attention(x)
batch_size, in_planes, height, width = x.size()
x = x * channel_attention
x = x.reshape(1, -1, height, width)
aggregate_weight = spatial_attention * kernel_attention * self.weight.unsqueeze(dim=0)
aggregate_weight = torch.sum(aggregate_weight, dim=1).view(
[-1, self.in_planes // self.groups, self.kernel_size, self.kernel_size])
output = F.conv2d(x, weight=aggregate_weight, bias=None, stride=self.stride, padding=self.padding,
dilation=self.dilation, groups=self.groups * batch_size)
output = output.view(batch_size, self.out_planes, output.size(-2), output.size(-1))
output = output * filter_attention
return output
def _forward_impl_pw1x(self, x):
channel_attention, filter_attention, spatial_attention, kernel_attention = self.attention(x)
x = x * channel_attention
output = F.conv2d(x, weight=self.weight.squeeze(dim=0), bias=None, stride=self.stride, padding=self.padding,
dilation=self.dilation, groups=self.groups)
output = output * filter_attention
return output
def forward(self, x):
return self._forward_impl(x)
3.2 建立一个yolov5-odconv.yaml文件
注意到，这里博主直接使用ODConv代替Head P5前一层的标准卷积(事实上可以替换结构中的任意标准卷积), 另外注意nc改为自己数据集的类别数。
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# Parameters
nc: 10 # 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 小目标
- [30,61, 62,45, 59,119] # P4/16 中目标
- [116,90, 156,198, 373,326] # P5/32 大目标
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2 output_channel, kernel_size, stride, padding
[-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, ODConv, [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)
]
3.3 将ODConv引入到yolo.py文件中
在下图的红色圈内位置处，引入相关的类即可。
3.4 修改train.py启动文件
修改配置文件为yolov5-odconv.yaml即可，如下图所示：
4. 总结
本篇博客主要介绍了轻量化多维动态卷积ODConv结构，多维度关注数据特征，减少计算量的同时保持精度稳定或略微上涨。另外，在修改过程中，要是有任何问题，评论区交流；如果博客对您有帮助，请帮忙点个赞，收藏一下；后续会持续更新本人实验当中觉得有用的点子，如果很感兴趣的话，可以关注一下，谢谢大家啦！