yolov5中，网络配置文件中的常用块（自用）

小伞cos

已于 2024-02-27 16:20:09 修改

阅读量507

点赞数 9

文章标签： YOLO 网络深度学习

于 2024-01-09 00:37:37 首次发布

本文链接：https://blog.csdn.net/weixin_68494476/article/details/135469422

版权

本文介绍了几种关键的深度学习模块，包括标准卷积、CSPBottleneck（带有三个卷积的CSP瓶颈）、SPPF（空间金字塔池化-快速）以及TransformerBlock，展示了它们在卷积神经网络中的结构和功能，尽管某些模块如大卷积和Transformer的效果被证实不如预期，但仍对现代IT技术中的图像处理有重要影响。

摘要由CSDN通过智能技术生成

1：卷积块

class Conv(nn.Module):
    # Standard convolution
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
        """
          Standard convolution  conv+BN+act
          :params c1: 输入的channel值
          :params c2: 输出的channel值
          :params k: 卷积的kernel_size
          :params s: 卷积的stride
          :params p: 卷积的padding  一般是None  可以通过autopad自行计算需要pad的padding数
          :params g: 卷积的groups数  =1就是普通的卷积  >1就是深度可分离卷积
          :params act: 激活函数类型   True就是SiLU()/Swish   False就是不使用激活函数
                       类型是nn.Module就使用传进来的激活函数类型
          　"""
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.SiLU() 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))

2：C3卷积块

class C3(nn.Module):
    # CSP Bottleneck with 3 convolutions
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)  # act=FReLU(c2)
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
        # self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])

    def forward(self, x):
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))

class Bottleneck(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_, c2, 3, 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))

3：SPPF模块

class SPPF(nn.Module):
    # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
        super().__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * 4, c2, 1, 1)
        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)

    def forward(self, x):
        x = self.cv1(x)
        with warnings.catch_warnings():
            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
            y1 = self.m(x)
            y2 = self.m(y1)
            return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))

已经弃用的

1：focus

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):  # ch_in, ch_out, kernel, stride, padding, groups
        super().__init__()
        self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
        # self.contract = Contract(gain=2)

    def forward(self, x):  # x(b,c,w,h) -> y(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))

换成大卷积和来提升感受视野

2：transformer

class TransformerBlock(nn.Module):
    # Vision Transformer https://arxiv.org/abs/2010.11929
    def __init__(self, c1, c2, num_heads, num_layers):
        super().__init__()
        self.conv = None
        if c1 != c2:
            self.conv = Conv(c1, c2)
        self.linear = nn.Linear(c2, c2)  # learnable position embedding
        self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers)))
        self.c2 = c2

    def forward(self, x):
        if self.conv is not None:
            x = self.conv(x)
        b, _, w, h = x.shape
        p = x.flatten(2).permute(2, 0, 1)
        return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, w, h)

class TransformerLayer(nn.Module):
    # Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)
    def __init__(self, c, num_heads):
        super().__init__()
        self.q = nn.Linear(c, c, bias=False)
        self.k = nn.Linear(c, c, bias=False)
        self.v = nn.Linear(c, c, bias=False)
        self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
        self.fc1 = nn.Linear(c, c, bias=False)
        self.fc2 = nn.Linear(c, c, bias=False)

    def forward(self, x):
        x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x
        x = self.fc2(self.fc1(x)) + x
        return x

实测效果不如大卷积，也已经弃用