YOLOv8重要文件解读

2023-12-15 18:40:35

🍨 本文为[🔗365天深度学习训练营学习记录博客
🍦 参考文章:365天深度学习训练营
🍖 原作者:[K同学啊 | 接辅导、项目定制]
🚀 文章来源:[K同学的学习圈子](https://www.yuque.com/mingtian-fkmxf/zxwb45)?

D:\ultralytics-main\ultralytics-main\ultralytics\nn\models\** 目录下的文件与YOLOv5commonpy中文件起到的作用相同,对应模型中的相应模块?。

conv.py文件?

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

函数的参数包括:

  • k:卷积核的大小,可以是整数或整数列表。
  • p:填充大小,可以是整数或整数列表,如果未提供,则自动计算。
  • d:膨胀率(dilation rate),默认为1。
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):
        """Initialize Conv layer with given arguments including activation."""
        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):
        """Apply convolution, batch normalization and activation to input tensor."""
        return self.act(self.bn(self.conv(x)))

    def forward_fuse(self, x):
        """Perform transposed convolution of 2D data."""
        return self.act(self.conv(x))


class Conv2(Conv):
    """Simplified RepConv module with Conv fusing."""

    def __init__(self, c1, c2, k=3, s=1, p=None, g=1, d=1, act=True):
        """Initialize Conv layer with given arguments including activation."""
        super().__init__(c1, c2, k, s, p, g=g, d=d, act=act)
        self.cv2 = nn.Conv2d(c1, c2, 1, s, autopad(1, p, d), groups=g, dilation=d, bias=False)  # add 1x1 conv

    def forward(self, x):
        """Apply convolution, batch normalization and activation to input tensor."""
        return self.act(self.bn(self.conv(x) + self.cv2(x)))

    def forward_fuse(self, x):
        """Apply fused convolution, batch normalization and activation to input tensor."""
        return self.act(self.bn(self.conv(x)))

    def fuse_convs(self):
        """Fuse parallel convolutions."""
        w = torch.zeros_like(self.conv.weight.data)
        i = [x // 2 for x in w.shape[2:]]
        w[:, :, i[0]:i[0] + 1, i[1]:i[1] + 1] = self.cv2.weight.data.clone()
        self.conv.weight.data += w
        self.__delattr__('cv2')
        self.forward = self.forward_fuse

__init__ 方法用于初始化卷积层,参数包括输入通道数 c1,输出通道数 c2,卷积核大小 k,步幅 s,填充大小 p,分组数 g,膨胀率 d,以及是否使用激活函数 act

class LightConv(nn.Module):
    """
    Light convolution with args(ch_in, ch_out, kernel).

    https://github.com/PaddlePaddle/PaddleDetection/blob/develop/ppdet/modeling/backbones/hgnet_v2.py
    """

    def __init__(self, c1, c2, k=1, act=nn.ReLU()):
        """Initialize Conv layer with given arguments including activation."""
        super().__init__()
        self.conv1 = Conv(c1, c2, 1, act=False)
        self.conv2 = DWConv(c2, c2, k, act=act)

    def forward(self, x):
        """Apply 2 convolutions to input tensor."""
        return self.conv2(self.conv1(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
        """Initialize Depth-wise convolution with given parameters."""
        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act)

LightConv类

  • LightConv 类表示轻量级卷积,包含两个卷积层的堆叠。

DWConv类

  • DWConv 类表示深度可分离卷积。
  • 在初始化过程中,调用了父类 Conv__init__ 方法,其中 g 参数被设置为输入通道数和输出通道数的最大公约数,从而实现深度可分离卷积。
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
        """Initialize DWConvTranspose2d class with given parameters."""
        super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2))


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):
        """Initialize ConvTranspose2d layer with batch normalization and activation function."""
        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):
        """Applies transposed convolutions, batch normalization and activation to input."""
        return self.act(self.bn(self.conv_transpose(x)))

    def forward_fuse(self, x):
        """Applies activation and convolution transpose operation to input."""
        return self.act(self.conv_transpose(x))
  1. DWConvTranspose2d类

    • DWConvTranspose2d 类表示深度可分离的转置卷积。
    • 在初始化过程中,调用了父类 nn.ConvTranspose2d__init__ 方法,并设置了 groups 参数为输入通道数和输出通道数的最大公约数。
  2. ConvTranspose类

    • ConvTranspose 类表示转置卷积 2D 层,与普通转置卷积相比,它包含了可选的批归一化和激活函数。
    • __init__ 方法用于初始化转置卷积,参数包括输入通道数 c1,输出通道数 c2,卷积核大小 k,步幅 s,填充参数 p,以及是否使用批归一化 bn 和激活函数 act
    • 在初始化过程中,创建了转置卷积层 conv_transpose,以及可选的批归一化层 bn 和激活函数 act
class Focus(nn.Module):
    """Focus wh information into c-space."""

    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):
        """Initializes Focus object with user defined channel, convolution, padding, group and activation values."""
        super().__init__()
        self.conv = Conv(c1 * 4, c2, k, s, p, g, act=act)
        # self.contract = Contract(gain=2)

    def forward(self, x):
        """
        Applies convolution to concatenated tensor and returns the output.

        Input shape is (b,c,w,h) and output shape is (b,4c,w/2,h/2).
        """
        return self.conv(torch.cat((x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]), 1))
        # return self.conv(self.contract(x))
  • Focus类(用于在通道维度上聚焦宽高信息

    • Focus 类继承自 nn.Module,表示将宽高信息集中到通道空间的操作。
    • 在初始化过程中,创建了一个包含四个输入通道的卷积层 self.conv。卷积层将四个通道的信息进行卷积操作,然后输出到通道维度上,用于集中宽高信息。
  • forward 方法:

    • forward 方法实现了前向传播操作。
    • 输入张量的形状为 (b, c, w, h),其中 b 是批量大小,c 是通道数,wh 是宽和高。
    • 通过 torch.cat 将输入张量沿着宽和高方向进行四次拼接,得到一个新的张量,形状为 (b, 4c, w/2, h/2)。
class GhostConv(nn.Module):
    """Ghost Convolution https://github.com/huawei-noah/ghostnet."""

    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):
        """Initializes the GhostConv object with input channels, output channels, kernel size, stride, groups and
        activation.
        """
        super().__init__()
        c_ = c2 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, k, s, None, g, act=act)
        self.cv2 = Conv(c_, c_, 5, 1, None, c_, act=act)

    def forward(self, x):
        """Forward propagation through a Ghost Bottleneck layer with skip connection."""
        y = self.cv1(x)
        return torch.cat((y, self.cv2(y)), 1)

Ghost Convolution 是通过两个卷积层组合的轻量级卷积操作,其主要功能是在保持模型轻量化的同时,增加网络的感受野和表征能力。

两个卷积层组合的轻量级卷积操作:

  • 首先在初始化两个卷积层?self.cv1 = Conv(c1, c_, k, s, None, g, act=act) self.cv2 = Conv(c_, c_, 5, 1, None, c_, act=act)
  • 在forward 方法中实现两个卷积层组合:y = self.cv1(x)?将输入张量 x 传递给第一个卷积层 self.cv1 进行卷积,得到输出张量 y?return torch.cat((y, self.cv2(y)), 1)?将输出张量 yself.cv2(y) 进行通道维度上的拼接,得到最终的输出。

文章来源:https://blog.csdn.net/qq_60245590/article/details/135022013
本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。