yolov5s中加入DCNv2（可变形卷积v2）
Requirement
torch>=1.8.1
torchvision>=0.9.1
实现步骤
1.测试环境是否满足要求
import torch
import torchvision.ops
from torch import nn
import math
class DCNv2(nn.Module):
def __init__(self,
in_channels,
out_channels,
kernel_size=3,
stride=1,
padding=1):
super(DCNv2, self).__init__()
self.in_channels = in_channels
self.out_channels = out_channels
self.kernel_size = kernel_size
self.stride = stride if type(stride) == tuple else (stride, stride)
self.padding = padding
self.weight = nn.Parameter(torch.Tensor(out_channels, in_channels, kernel_size, kernel_size))
self.bias = nn.Parameter(torch.Tensor(out_channels))
self.conv_offset_mask = nn.Conv2d(in_channels,
3 * kernel_size * kernel_size,
kernel_size=kernel_size,
stride=stride,
padding=self.padding,
bias=True)
self.reset_parameters()
self._init_weight()
def reset_parameters(self):
n = self.in_channels * (self.kernel_size**2)
stdv = 1. / math.sqrt(n)
self.weight.data.uniform_(-stdv, stdv)
self.bias.data.zero_()
def _init_weight(self):
nn.init.constant_(self.conv_offset_mask.weight, 0.)
nn.init.constant_(self.conv_offset_mask.bias, 0.)
def forward(self, x):
out = self.conv_offset_mask(x)
o1, o2, mask = torch.chunk(out, 3, dim=1)
offset = torch.cat((o1, o2), dim=1)
mask = torch.sigmoid(mask)
x = torchvision.ops.deform_conv2d(input=x,
offset=offset,
weight=self.weight,
bias=self.bias,
padding=self.padding,
mask=mask,
stride=self.stride)
return x
model = nn.Sequential(
DCNv2(3, 32, kernel_size=3, stride=1, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(2, 2),
DCNv2(32, 32, kernel_size=3, stride=1, padding=1),
DCNv2(32, 64, kernel_size=3, stride=1, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(2, 2),
DCNv2(64, 64, kernel_size=3, stride=1, padding=1),
DCNv2(64, 128, kernel_size=3, stride=1, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(2, 2),
DCNv2(128, 128, kernel_size=3, stride=1, padding=1),
DCNv2(128, 256, kernel_size=3, stride=1, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(2, 2)
)
x = torch.randn(2, 3, 64, 64)
y = model(x)
print(x.size())
print(y.size())
"""
torch.Size([2, 3, 64, 64])
torch.Size([2, 256, 4, 4])
"""
如果能输出，则说明环境适配。
2.修改models/yolov5s.yaml
nc: 1
depth_multiple: 0.33
width_multiple: 0.50
anchors:
- [10,13, 16,30, 33,23]
- [30,61, 62,45, 59,119]
- [116,90, 156,198, 373,326]
backbone:
[[-1, 1, Conv, [64, 6, 2, 2]],
[-1, 1, DCNv2, [128, 3, 2]],
[-1, 3, C3, [128]],
[-1, 1, DCNv2, [256, 3, 2]],
[-1, 6, C3, [256]],
[-1, 1, DCNv2, [512, 3, 2]],
[-1, 9, C3, [512]],
[-1, 1, DCNv2, [1024, 3, 2]],
[-1, 3, C3, [1024]],
[-1, 1, SPPF, [1024, 5]],
]
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]],
[-1, 3, C3, [512, False]],
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]],
[-1, 3, C3, [256, False]],
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]],
[-1, 3, C3, [512, False]],
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]],
[-1, 3, C3, [1024, False]],
[[17, 20, 23], 1, Detect, [nc, anchors]],
]
3.修改models/common.py
class DCNv2(nn.Module):
def __init__(self,
in_channels,
out_channels,
kernel_size=3,
stride=1,
padding=1):
super(DCNv2, self).__init__()
self.in_channels = in_channels
self.out_channels = out_channels
self.kernel_size = kernel_size
self.stride = stride if type(stride) == tuple else (stride, stride)
self.padding = padding
self.weight = nn.Parameter(torch.Tensor(out_channels, in_channels, kernel_size, kernel_size))
self.bias = nn.Parameter(torch.Tensor(out_channels))
self.conv_offset_mask = nn.Conv2d(in_channels,
3 * kernel_size * kernel_size,
kernel_size=kernel_size,
stride=stride,
padding=self.padding,
bias=True)
self.reset_parameters()
self._init_weight()
def reset_parameters(self):
n = self.in_channels * (self.kernel_size**2)
stdv = 1. / math.sqrt(n)
self.weight.data.uniform_(-stdv, stdv)
self.bias.data.zero_()
def _init_weight(self):
nn.init.constant_(self.conv_offset_mask.weight, 0.)
nn.init.constant_(self.conv_offset_mask.bias, 0.)
def forward(self, x):
out = self.conv_offset_mask(x)
o1, o2, mask = torch.chunk(out, 3, dim=1)
offset = torch.cat((o1, o2), dim=1)
mask = torch.sigmoid(mask)
x = torchvision.ops.deform_conv2d(input=x,
offset=offset,
weight=self.weight,
bias=self.bias,
padding=self.padding,
mask=mask,
stride=self.stride)
return x
4.修改models/yolo.py
if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,BottleneckCSP, C3]:
if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,BottleneckCSP, C3, DCNv2]:
完成以上操作后，在train.py中导入对应的yaml文件和确认参数，即可开始训练。
参考
【1】 https://blog.csdn.net/shuaijieer/article/details/126249088
【2】 https://github.com/yjh0410/PyTorch_DCNv2Original: https://blog.csdn.net/weixin_42550418/article/details/128037557
Author: just f
Title: 【yolov5s中加入DCNv2（可变形卷积v2）】
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/787996/
转载文章受原作者版权保护。转载请注明原作者出处！