YOLOv8重要文件解读
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的__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))-
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的__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。
-
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，w和h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y和self.cv2(y)进行通道维度上的拼接，得到最终的输出。