常见特征金字塔模块代码实现

1.引言

特征金字塔模块是一种常用的计算机视觉算法，用于多尺度目标检测和分类。它通过在不同尺度上提取图像特征，并将这些特征组合成一个金字塔状的结构，使得算法可以同时处理不同尺度的目标。这个金字塔状的特征结构可以被用来提高特征的稳定性，减小误差，并提高算法的准确性。在物体检测方面，特征金字塔模块可用于检测较小目标、避免目标漏检和减小误检率。

如何在yolov8中使用这些特征金字塔模块
点击此贴

2.特征金字塔模块

2.1 SPP

SPP作为最早的特征金字塔之一
代码如下：

class SPP(nn.Module):
    # Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
    def __init__(self, c1, c2, k=(5, 9, 13)):
        super().__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])

    def forward(self, x):
        x = self.cv1(x)
        return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))

2.2 SPPF

SPPF是目前最为流行的特征金字塔，yolov5，yolov8均使用的SPPF

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)
        y1 = self.m(x)
        y2 = self.m(y1)
        return self.cv2(torch.cat((x, y1, y2, self.m(y2)), 1))

2.3 ASPP

# without BN version
class ASPP(nn.Module):
    def __init__(self, in_channel = 512, out_channel = 256):
        super(ASPP, self).__init__()
        self.mean = nn.AdaptiveAvgPool2d((1, 1))  # (1,1)means ouput_dim
        self.conv = nn.Conv2d(in_channel,out_channel, 1, 1)
        self.atrous_block1 = nn.Conv2d(in_channel, out_channel, 1, 1)
        self.atrous_block6 = nn.Conv2d(in_channel, out_channel, 3, 1, padding=6, dilation=6)
        self.atrous_block12 = nn.Conv2d(in_channel, out_channel, 3, 1, padding=12, dilation=12)
        self.atrous_block18 = nn.Conv2d(in_channel, out_channel, 3, 1, padding=18, dilation=18)
        self.conv_1x1_output = nn.Conv2d(out_channel * 5, out_channel, 1, 1)

    def forward(self, x):
        size = x.shape[2:]

        image_features = self.mean(x)
        image_features = self.conv(image_features)
        # image_features = F.upsample(image_features, size=size, mode='bilinear')
        #上面一句报错，自行修改
        # image_features = nn.Upsample(image_features, size=size, mode='bilinear')
        image_features = nn.functional.interpolate(image_features, size=size, mode='bilinear')
        atrous_block1 = self.atrous_block1(x)
        atrous_block6 = self.atrous_block6(x)
        atrous_block12 = self.atrous_block12(x)
        atrous_block18 = self.atrous_block18(x)

        net = self.conv_1x1_output(torch.cat([image_features, atrous_block1, atrous_block6,
                                              atrous_block12, atrous_block18], dim=1))
        return net

2.4 SimSPPF

class SimConv(nn.Module):
    '''Normal Conv with ReLU activation'''
    def __init__(self, in_channels, out_channels, kernel_size, stride, groups=1, bias=False):
        super().__init__()
        padding = kernel_size // 2
        self.conv = nn.Conv2d(
            in_channels,
            out_channels,
            kernel_size=kernel_size,
            stride=stride,
            padding=padding,
            groups=groups,
            bias=bias,
        )
        self.bn = nn.BatchNorm2d(out_channels)
        self.act = nn.ReLU()

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

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

class SimSPPF(nn.Module):
    '''Simplified SPPF with ReLU activation'''
    def __init__(self, in_channels, out_channels, kernel_size=5):
        super().__init__()
        c_ = in_channels // 2  # hidden channels
        self.cv1 = SimConv(in_channels, c_, 1, 1)
        self.cv2 = SimConv(c_ * 4, out_channels, 1, 1)
        self.m = nn.MaxPool2d(kernel_size=kernel_size, stride=1, padding=kernel_size // 2)

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

2.5 SPPCSPC

class SPPCSPC(nn.Module):
    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=(5, 9, 13)):
        super(SPPCSPC, self).__init__()
        c_ = int(2 * c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(c_, c_, 3, 1)
        self.cv4 = Conv(c_, c_, 1, 1)
        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
        self.cv5 = Conv(4 * c_, c_, 1, 1)
        self.cv6 = Conv(c_, c_, 3, 1)
        self.cv7 = Conv(2 * c_, c2, 1, 1)

    def forward(self, x):
        x1 = self.cv4(self.cv3(self.cv1(x)))
        y1 = self.cv6(self.cv5(torch.cat([x1] + [m(x1) for m in self.m], 1)))
        y2 = self.cv2(x)
        return self.cv7(torch.cat((y1, y2), dim=1))

2.6 SPPFCSPC

class SPPFCSPC(nn.Module):
    
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=5):
        super(SPPFCSPC, self).__init__()
        c_ = int(2 * c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(c_, c_, 3, 1)
        self.cv4 = Conv(c_, c_, 1, 1)
        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
        self.cv5 = Conv(4 * c_, c_, 1, 1)
        self.cv6 = Conv(c_, c_, 3, 1)
        self.cv7 = Conv(2 * c_, c2, 1, 1)

    def forward(self, x):
        x1 = self.cv4(self.cv3(self.cv1(x)))
        x2 = self.m(x1)
        x3 = self.m(x2)
        y1 = self.cv6(self.cv5(torch.cat((x1,x2,x3, self.m(x3)),1)))
        y2 = self.cv2(x)
        return self.cv7(torch.cat((y1, y2), dim=1))