yolov5添加damoyolo GFPN模块

DAMO yolo在提出前阿里就推出了一个叫GIRAFFEDET的模型，主推轻backbone重neck的网络结构，使得网络更关注于高分辨率特征图中空间信息和低分辨率特征图中语义信息的信息交互。同时这个设计范式允许检测网络在网络早期阶段就以相同优先级处理高层语义信息和低层空间信息，使其在检测任务上更加有效。

感兴趣的可以看一下GIRAFFEDET的原文：

《GiraffeDet: A Heavy-Neck Paradigm for Object Detection》

不过这里主要讲的不是 GiraffeDet，而是将这一思想应用在yolov5中。

先看一下DAMO yolo中Giraffe Neck的结构：

 上重点：

在yolov5的工程中的models文件夹创建yolov5s-GFPN.yaml

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license

# 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
  ]

# DAMO-YOLO GFPN Head
head:
  [[-1, 1, Conv, [512, 1, 1]], # 10
   [6, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],
   [-1, 3, CSPStage, [512]], # 13

   [-1, 1, nn.Upsample, [None, 2, 'nearest']], #14
   [4, 1, Conv, [256, 3, 2]], # 15
   [[14, -1, 6], 1, Concat, [1]],
   [-1, 3, CSPStage, [512]], # 17

   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],
   [-1, 3, CSPStage, [256]], # 20

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 17], 1, Concat, [1]],
   [-1, 3, CSPStage, [512]], # 23

   [17, 1, Conv, [256, 3, 2]], # 24
   [23, 1, Conv, [256, 3, 2]], # 25
   [[13, 24, -1], 1, Concat, [1]],
   [-1, 3, CSPStage, [1024]], # 27

   [[20, 23, 27], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

 在common.py中添加如下代码：

def conv_bn(in_channels, out_channels, kernel_size, stride, padding, groups=1):
    '''Basic cell for rep-style block, including conv and bn'''
    result = nn.Sequential()
    result.add_module(
        'conv',
        nn.Conv2d(in_channels=in_channels,
                  out_channels=out_channels,
                  kernel_size=kernel_size,
                  stride=stride,
                  padding=padding,
                  groups=groups,
                  bias=False))
    result.add_module('bn', nn.BatchNorm2d(num_features=out_channels))
    return result


class RepConv(nn.Module):
    '''RepConv is a basic rep-style block, including training and deploy status
    Code is based on https://github.com/DingXiaoH/RepVGG/blob/main/repvgg.py
    '''

    def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size=3,
                 stride=1,
                 padding=1,
                 dilation=1,
                 groups=1,
                 padding_mode='zeros',
                 deploy=False,
                 act='relu',
                 norm=None):
        super(RepConv, self).__init__()
        self.deploy = deploy
        self.groups = groups
        self.in_channels = in_channels
        self.out_channels = out_channels

        assert kernel_size == 3
        assert padding == 1

        padding_11 = padding - kernel_size // 2

        if isinstance(act, str):
            self.nonlinearity = get_activation(act)
        else:
            self.nonlinearity = act

        if deploy:
            self.rbr_reparam = nn.Conv2d(in_channels=in_channels,
                                         out_channels=out_channels,
                                         kernel_size=kernel_size,
                                         stride=stride,
                                         padding=padding,
                                         dilation=dilation,
                                         groups=groups,
                                         bias=True,
                                         padding_mode=padding_mode)

        else:
            self.rbr_identity = None
            self.rbr_dense = conv_bn(in_channels=in_channels,
                                     out_channels=out_channels,
                                     kernel_size=kernel_size,
                                     stride=stride,
                                     padding=padding,
                                     groups=groups)
            self.rbr_1x1 = conv_bn(in_channels=in_channels,
                                   out_channels=out_channels,
                                   kernel_size=1,
                                   stride=stride,
                                   padding=padding_11,
                                   groups=groups)

    def forward(self, inputs):
        '''Forward process'''
        if hasattr(self, 'rbr_reparam'):
            return self.nonlinearity(self.rbr_reparam(inputs))

        if self.rbr_identity is None:
            id_out = 0
        else:
            id_out = self.rbr_identity(inputs)

        return self.nonlinearity(
            self.rbr_dense(inputs) + self.rbr_1x1(inputs) + id_out)

    def get_equivalent_kernel_bias(self):
        kernel3x3, bias3x3 = self._fuse_bn_tensor(self.rbr_dense)
        kernel1x1, bias1x1 = self._fuse_bn_tensor(self.rbr_1x1)
        kernelid, biasid = self._fuse_bn_tensor(self.rbr_identity)
        return kernel3x3 + self._pad_1x1_to_3x3_tensor(
            kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid

    def _pad_1x1_to_3x3_tensor(self, kernel1x1):
        if kernel1x1 is None:
            return 0
        else:
            return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1])

    def _fuse_bn_tensor(self, branch):
        if branch is None:
            return 0, 0
        if isinstance(branch, nn.Sequential):
            kernel = branch.conv.weight
            running_mean = branch.bn.running_mean
            running_var = branch.bn.running_var
            gamma = branch.bn.weight
            beta = branch.bn.bias
            eps = branch.bn.eps
        else:
            assert isinstance(branch, nn.BatchNorm2d)
            if not hasattr(self, 'id_tensor'):
                input_dim = self.in_channels // self.groups
                kernel_value = np.zeros((self.in_channels, input_dim, 3, 3),
                                        dtype=np.float32)
                for i in range(self.in_channels):
                    kernel_value[i, i % input_dim, 1, 1] = 1
                self.id_tensor = torch.from_numpy(kernel_value).to(
                    branch.weight.device)
            kernel = self.id_tensor
            running_mean = branch.running_mean
            running_var = branch.running_var
            gamma = branch.weight
            beta = branch.bias
            eps = branch.eps
        std = (running_var + eps).sqrt()
        t = (gamma / std).reshape(-1, 1, 1, 1)
        return kernel * t, beta - running_mean * gamma / std

    def switch_to_deploy(self):
        if hasattr(self, 'rbr_reparam'):
            return
        kernel, bias = self.get_equivalent_kernel_bias()
        self.rbr_reparam = nn.Conv2d(
            in_channels=self.rbr_dense.conv.in_channels,
            out_channels=self.rbr_dense.conv.out_channels,
            kernel_size=self.rbr_dense.conv.kernel_size,
            stride=self.rbr_dense.conv.stride,
            padding=self.rbr_dense.conv.padding,
            dilation=self.rbr_dense.conv.dilation,
            groups=self.rbr_dense.conv.groups,
            bias=True)
        self.rbr_reparam.weight.data = kernel
        self.rbr_reparam.bias.data = bias
        for para in self.parameters():
            para.detach_()
        self.__delattr__('rbr_dense')
        self.__delattr__('rbr_1x1')
        if hasattr(self, 'rbr_identity'):
            self.__delattr__('rbr_identity')
        if hasattr(self, 'id_tensor'):
            self.__delattr__('id_tensor')
        self.deploy = True


class Swish(nn.Module):
    def __init__(self, inplace=True):
        super(Swish, self).__init__()
        self.inplace = inplace

    def forward(self, x):
        if self.inplace:
            x.mul_(F.sigmoid(x))
            return x
        else:
            return x * F.sigmoid(x)


def get_activation(name='silu', inplace=True):
    if name is None:
        return nn.Identity()

    if isinstance(name, str):
        if name == 'silu':
            module = nn.SiLU(inplace=inplace)
        elif name == 'relu':
            module = nn.ReLU(inplace=inplace)
        elif name == 'lrelu':
            module = nn.LeakyReLU(0.1, inplace=inplace)
        elif name == 'swish':
            module = Swish(inplace=inplace)
        elif name == 'hardsigmoid':
            module = nn.Hardsigmoid(inplace=inplace)
        elif name == 'identity':
            module = nn.Identity()
        else:
            raise AttributeError('Unsupported act type: {}'.format(name))
        return module

    elif isinstance(name, nn.Module):
        return name

    else:
        raise AttributeError('Unsupported act type: {}'.format(name))


def get_norm(name, out_channels, inplace=True):
    if name == 'bn':
        module = nn.BatchNorm2d(out_channels)
    else:
        raise NotImplementedError
    return module


class ConvBNAct(nn.Module):
    """A Conv2d -> Batchnorm -> silu/leaky relu block"""

    def __init__(
            self,
            in_channels,
            out_channels,
            ksize,
            stride=1,
            groups=1,
            bias=False,
            act='silu',
            norm='bn',
            reparam=False,
    ):
        super().__init__()
        # same padding
        pad = (ksize - 1) // 2
        self.conv = nn.Conv2d(
            in_channels,
            out_channels,
            kernel_size=ksize,
            stride=stride,
            padding=pad,
            groups=groups,
            bias=bias,
        )
        if norm is not None:
            self.bn = get_norm(norm, out_channels, inplace=True)
        if act is not None:
            self.act = get_activation(act, inplace=True)
        self.with_norm = norm is not None
        self.with_act = act is not None

    def forward(self, x):
        x = self.conv(x)
        if self.with_norm:
            x = self.bn(x)
        if self.with_act:
            x = self.act(x)
        return x

    def fuseforward(self, x):
        return self.act(self.conv(x))


class BasicBlock_3x3_Reverse(nn.Module):
    def __init__(self,
                 ch_in,
                 ch_hidden_ratio,
                 ch_out,
                 act='relu',
                 shortcut=True):
        super(BasicBlock_3x3_Reverse, self).__init__()
        assert ch_in == ch_out
        ch_hidden = int(ch_in * ch_hidden_ratio)
        self.conv1 = ConvBNAct(ch_hidden, ch_out, 3, stride=1, act=act)
        self.conv2 = RepConv(ch_in, ch_hidden, 3, stride=1, act=act)
        self.shortcut = shortcut

    def forward(self, x):
        y = self.conv2(x)
        y = self.conv1(y)
        if self.shortcut:
            return x + y
        else:
            return y


class SPP(nn.Module):
    def __init__(
            self,
            ch_in,
            ch_out,
            k,
            pool_size,
            act='swish',
    ):
        super(SPP, self).__init__()
        self.pool = []
        for i, size in enumerate(pool_size):
            pool = nn.MaxPool2d(kernel_size=size,
                                stride=1,
                                padding=size // 2,
                                ceil_mode=False)
            self.add_module('pool{}'.format(i), pool)
            self.pool.append(pool)
        self.conv = ConvBNAct(ch_in, ch_out, k, act=act)

    def forward(self, x):
        outs = [x]

        for pool in self.pool:
            outs.append(pool(x))
        y = torch.cat(outs, axis=1)

        y = self.conv(y)
        return y


class CSPStage(nn.Module):
    def __init__(self,
                 ch_in,
                 ch_out,
                 n,
                 block_fn='BasicBlock_3x3_Reverse',
                 ch_hidden_ratio=1.0,
                 act='silu',
                 spp=False):
        super(CSPStage, self).__init__()

        split_ratio = 2
        ch_first = int(ch_out // split_ratio)
        ch_mid = int(ch_out - ch_first)
        self.conv1 = ConvBNAct(ch_in, ch_first, 1, act=act)
        self.conv2 = ConvBNAct(ch_in, ch_mid, 1, act=act)
        self.convs = nn.Sequential()

        next_ch_in = ch_mid
        for i in range(n):
            if block_fn == 'BasicBlock_3x3_Reverse':
                self.convs.add_module(
                    str(i),
                    BasicBlock_3x3_Reverse(next_ch_in,
                                           ch_hidden_ratio,
                                           ch_mid,
                                           act=act,
                                           shortcut=True))
            else:
                raise NotImplementedError
            if i == (n - 1) // 2 and spp:
                self.convs.add_module(
                    'spp', SPP(ch_mid * 4, ch_mid, 1, [5, 9, 13], act=act))
            next_ch_in = ch_mid
        self.conv3 = ConvBNAct(ch_mid * n + ch_first, ch_out, 1, act=act)

    def forward(self, x):
        y1 = self.conv1(x)
        y2 = self.conv2(x)

        mid_out = [y1]
        for conv in self.convs:
            y2 = conv(y2)
            mid_out.append(y2)
        y = torch.cat(mid_out, axis=1)
        y = self.conv3(y)
        return y

 同时在yolo.py中的parse_model函数中添加：

        if m in (Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
                 BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x, CSPStage):
            c1, c2 = ch[f], args[0]
            if c2 != no:  # if not output
                c2 = make_divisible(c2 * gw, 8)

            args = [c1, c2, *args[1:]]
            if m in [BottleneckCSP, C3, C3TR, C3Ghost, C3x, CSPStage]:
                args.insert(2, n)  # number of repeats
                n = 1

在yolo.py中找到 BaseModel()在其中的fuse函数中添加：

            if isinstance(m, RepConv):
                # print(f" fuse_repvgg_block")
                m.switch_to_deploy()

以上步骤即完成模块的添加。

在conda环境中执行如下指令即可开始训练：

python train.py --data coco.yaml --epochs 300 --weights '' --cfg yolov5s-GFPN.yaml  --batch-size 32