YOLOv9

모델을 구성하는 common.py에 대한 클래스 및 함수 구성요소에 대해 알아보자

본 포스트는 추가 설명 없이 함수나 클래스에 대한 코드만 존재한다(주석으로 간단히 설명할 것이다)

def autopad(k, p=None, d=1): # kernel, padding, dilation
	# Pad to 'same' shape outputs
    if d > 1:
    	k =d*(k-1) + 1 if isinstance(k, int) else [d * (x-1) + 1 for x in k] # actual kernel-size
    if p is None:
    	p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
    return p

class Conv(nn.Module):
	# Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)
    default_act = nn.SiLU()	# default activation
    
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
    	super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()
        
    def forward(self, x):
    	return self.act(self.bn(self.conv(X)))
        
    def forward_fuse(self, x):
    	return self.act(self.conv(x))

class AConv(nn.Module):
    def __init__(self, c1, c2):  # ch_in, ch_out, shortcut, kernels, groups, expand
        super().__init__()
        self.cv1 = Conv(c1, c2, 3, 2, 1)

    def forward(self, x):
        x = torch.nn.functional.avg_pool2d(x, 2, 1, 0, False, True)
        return self.cv1(x)

class ADown(nn.Module):
    def __init__(self, c1, c2):  # ch_in, ch_out, shortcut, kernels, groups, expand
        super().__init__()
        self.c = c2 // 2
        self.cv1 = Conv(c1 // 2, self.c, 3, 2, 1)
        self.cv2 = Conv(c1 // 2, self.c, 1, 1, 0)

    def forward(self, x):
        x = torch.nn.functional.avg_pool2d(x, 2, 1, 0, False, True)
        x1,x2 = x.chunk(2, 1)
        x1 = self.cv1(x1)
        x2 = torch.nn.functional.max_pool2d(x2, 3, 2, 1)
        x2 = self.cv2(x2)
        return torch.cat((x1, x2), 1)

class RepConvN(nn.Module):
    """RepConv is a basic rep-style block, including training and deploy status
    This code is based on https://github.com/DingXiaoH/RepVGG/blob/main/repvgg.py
    """
    default_act = nn.SiLU()  # default activation

    def __init__(self, c1, c2, k=3, s=1, p=1, g=1, d=1, act=True, bn=False, deploy=False):
        super().__init__()
        assert k == 3 and p == 1
        self.g = g
        self.c1 = c1
        self.c2 = c2
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

        self.bn = None
        self.conv1 = Conv(c1, c2, k, s, p=p, g=g, act=False)
        self.conv2 = Conv(c1, c2, 1, s, p=(p - k // 2), g=g, act=False)

    def forward_fuse(self, x):
        """Forward process"""
        return self.act(self.conv(x))

    def forward(self, x):
        """Forward process"""
        id_out = 0 if self.bn is None else self.bn(x)
        return self.act(self.conv1(x) + self.conv2(x) + id_out)

    def get_equivalent_kernel_bias(self):
        kernel3x3, bias3x3 = self._fuse_bn_tensor(self.conv1)
        kernel1x1, bias1x1 = self._fuse_bn_tensor(self.conv2)
        kernelid, biasid = self._fuse_bn_tensor(self.bn)
        return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid

    def _avg_to_3x3_tensor(self, avgp):
        channels = self.c1
        groups = self.g
        kernel_size = avgp.kernel_size
        input_dim = channels // groups
        k = torch.zeros((channels, input_dim, kernel_size, kernel_size))
        k[np.arange(channels), np.tile(np.arange(input_dim), groups), :, :] = 1.0 / kernel_size ** 2
        return k

    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, Conv):
            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
        elif isinstance(branch, nn.BatchNorm2d):
            if not hasattr(self, 'id_tensor'):
                input_dim = self.c1 // self.g
                kernel_value = np.zeros((self.c1, input_dim, 3, 3), dtype=np.float32)
                for i in range(self.c1):
                    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 fuse_convs(self):
        if hasattr(self, 'conv'):
            return
        kernel, bias = self.get_equivalent_kernel_bias()
        self.conv = nn.Conv2d(in_channels=self.conv1.conv.in_channels,
                              out_channels=self.conv1.conv.out_channels,
                              kernel_size=self.conv1.conv.kernel_size,
                              stride=self.conv1.conv.stride,
                              padding=self.conv1.conv.padding,
                              dilation=self.conv1.conv.dilation,
                              groups=self.conv1.conv.groups,
                              bias=True).requires_grad_(False)
        self.conv.weight.data = kernel
        self.conv.bias.data = bias
        for para in self.parameters():
            para.detach_()
        self.__delattr__('conv1')
        self.__delattr__('conv2')
        if hasattr(self, 'nm'):
            self.__delattr__('nm')
        if hasattr(self, 'bn'):
            self.__delattr__('bn')
        if hasattr(self, 'id_tensor'):
            self.__delattr__('id_tensor')

class SP(nn.Module):
    def __init__(self, k=3, s=1):
        super(SP, self).__init__()
        self.m = nn.MaxPool2d(kernel_size=k, stride=s, padding=k // 2)

    def forward(self, x):
        return self.m(x)

class MP(nn.Module):
    # Max pooling
    def __init__(self, k=2):
        super(MP, self).__init__()
        self.m = nn.MaxPool2d(kernel_size=k, stride=k)

    def forward(self, x):
        return self.m(x)

class ConvTranspose(nn.Module):
    # Convolution transpose 2d layer
    default_act = nn.SiLU()  # default activation

    def __init__(self, c1, c2, k=2, s=2, p=0, bn=True, act=True):
        super().__init__()
        self.conv_transpose = nn.ConvTranspose2d(c1, c2, k, s, p, bias=not bn)
        self.bn = nn.BatchNorm2d(c2) if bn else nn.Identity()
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

    def forward(self, x):
        return self.act(self.bn(self.conv_transpose(x)))

class DWConv(Conv):
    # Depth-wise convolution
    def __init__(self, c1, c2, k=1, s=1, d=1, act=True):  # ch_in, ch_out, kernel, stride, dilation, activation
        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)

class DWConvTranspose2d(nn.ConvTranspose2d):
    # Depth-wise transpose convolution
    def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0):  # ch_in, ch_out, kernel, stride, padding, padding_out
        super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2))