YOLOv8添加DCNv2可变形卷积

最近比较火的可变形卷积（Deformable Convolutional Networks(DCN)）被称为目标检测改进网络结构的中涨点神器，确实在yolov8中加入DCN3可以涨3到4个点，尤其是它对小目标检测效果较好。下面是对DCNv2添加记录一下

首先我们要在nn/models/文件夹下block.py文件中加入以下代码

class DCNv2(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size, stride=1,
                 padding=1, dilation=1, groups=1, deformable_groups=1):
        super(DCNv2, self).__init__()

        self.in_channels = in_channels
        self.out_channels = out_channels
        self.kernel_size = (kernel_size, kernel_size)
        self.stride = (stride, stride)
        self.padding = (padding, padding)
        self.dilation = (dilation, dilation)
        self.groups = groups
        self.deformable_groups = deformable_groups

        self.weight = nn.Parameter(
            torch.empty(out_channels, in_channels, *self.kernel_size)
        )
        self.bias = nn.Parameter(torch.empty(out_channels))

        out_channels_offset_mask = (self.deformable_groups * 3 *
                                    self.kernel_size[0] * self.kernel_size[1])
        self.conv_offset_mask = nn.Conv2d(
            self.in_channels,
            out_channels_offset_mask,
            kernel_size=self.kernel_size,
            stride=self.stride,
            padding=self.padding,
            bias=True,
        )
        self.bn = nn.BatchNorm2d(out_channels)
        self.act = Conv.default_act
        self.reset_parameters()

    def forward(self, x):
        offset_mask = self.conv_offset_mask(x)
        o1, o2, mask = torch.chunk(offset_mask, 3, dim=1)
        offset = torch.cat((o1, o2), dim=1)
        mask = torch.sigmoid(mask)
        x = torch.ops.torchvision.deform_conv2d(
            x,
            self.weight,
            offset,
            mask,
            self.bias,
            self.stride[0], self.stride[1],
            self.padding[0], self.padding[1],
            self.dilation[0], self.dilation[1],
            self.groups,
            self.deformable_groups,
            True
        )
        x = self.bn(x)
        x = self.act(x)
        return x

    def reset_parameters(self):
        n = self.in_channels
        for k in self.kernel_size:
            n *= k
        std = 1. / math.sqrt(n)
        self.weight.data.uniform_(-std, std)
        self.bias.data.zero_()
        self.conv_offset_mask.weight.data.zero_()
        self.conv_offset_mask.bias.data.zero_()


class Bottleneck_DCN(nn.Module):
    # Standard bottleneck with DCN
    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):  # ch_in, ch_out, shortcut, groups, kernels, expand
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        if k[0] == 3:
            self.cv1 = DCNv2(c1, c_, k[0], 1)
        else:
            self.cv1 = Conv(c1, c_, k[0], 1)
        if k[1] == 3:
            self.cv2 = DCNv2(c_, c2, k[1], 1, groups=g)
        else:
            self.cv2 = Conv(c_, c2, k[1], 1, g=g)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))


class C2f_DCN(nn.Module):
    # CSP Bottleneck with 2 convolutions
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        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_DCN(self.c, self.c, shortcut, g, k=(3, 3), e=1.0) for _ in range(n))

    def forward(self, x):
        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))

然后在tasks.py文件

这三处()里都加上C2f_DCN，接着在modules文件夹下的__init__.py

 来declare一下，否则会导入失败，至此已经差不多就ok了，现在只需要在yaml中你想要更改的网络结构的地方改一下就行，然后就可以训练了，如果不确定可以在训练的时候看一下print的网络结构即可。

下面是DCNv3的代码，操作跟上述有些不同，需要去GitHub上下载ops_dcnv3模块，然后进行编译，具体怎么弄可以私信我，如果我有时间的话，因为DCNv3配置起来还是比较麻烦的

class DCNV3_YoLo(nn.Module):
    def __init__(self, inc, ouc, k=1, s=1, p=None, g=1, d=1, act=True):
        super().__init__()

        self.conv = Conv(inc, ouc, k=1)
        self.dcnv3 = DCNv3(ouc, kernel_size=k, stride=s, group=g, dilation=d)
        self.bn = nn.BatchNorm2d(ouc)
        self.act = Conv.default_act

    def forward(self, x):
        x = self.conv(x)
        x = x.permute(0, 2, 3, 1)
        x = self.dcnv3(x)
        x = x.permute(0, 3, 1, 2)
        x = self.act(self.bn(x))
        return x

class Bottleneck_DCNV3(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):  # ch_in, ch_out, shortcut, groups, kernels, expand
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = DCNV3_YoLo(c_, c2, k[1], 1, g=g)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))

class DCNV3(nn.Module):
    # CSP Bottleneck with 2 convolutions
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        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_DCNV3(self.c, self.c, shortcut, g, k=(3, 3), e=1.0) for _ in range(n))

    def forward(self, x):
        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):
        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))