yolov5魔改教程之注意力机制

# ACON https://arxiv.org/pdf/2009.04759.pdf ----------------------------------------------------------------------------

class AconC(nn.Module):
    r""" ACON activation (activate or not).
    AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter
    according to "Activate or Not: Learning Customized Activation" [https://arxiv.org/pdf/2009.04759.pdf](https://arxiv.org/pdf/2009.04759.pdf).
    """

    def__init__(self, c1):
        super().__init__()
        # nn.Parameter的作用是：将一个不可训练的类型Tensor转换成可以训练的类型parameter
        # 并且会向宿主模型注册该参数 成为其一部分 即model.parameters()会包含这个parameter
        # 从而在参数优化的时候可以自动一起优化
        self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
        self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
        self.beta = nn.Parameter(torch.ones(1, c1, 1, 1))

    def forward(self, x):
        dpx = (self.p1 - self.p2) * x
        return dpx * torch.sigmoid(self.beta * dpx) + self.p2 * x

class MetaAconC(nn.Module):
    r""" ACON activation (activate or not).
    MetaAconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is generated by a small network
    according to "Activate or Not: Learning Customized Activation" [https://arxiv.org/pdf/2009.04759.pdf](https://arxiv.org/pdf/2009.04759.pdf).
    """

    def__init__(self, c1, k=1, s=1, r=16):  # ch_in, kernel, stride, r
        super().__init__()
        # 为了减少参数我们在两个中间的channel加了个缩放参数r，默认设置为16
        c2 = max(r, c1 // r)
        self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
        self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
        self.fc1 = nn.Conv2d(c1, c2, k, s, bias=True)
        self.fc2 = nn.Conv2d(c2, c1, k, s, bias=True)
        # self.bn1 = nn.BatchNorm2d(c2)
        # self.bn2 = nn.BatchNorm2d(c1)

    def forward(self, x):
        # 自适应函数的设计空间包含了layer-wise, channel-wise, pixel-wise这三种空间 分别对应的是层, 通道, 像素
        # 这里我们选择了channel-wise 首先分别对H, W维度求均值 然后通过两个卷积层 使得每一个通道所有像素共享一个权重
        # 最后由sigmoid激活函数求得beta
        y = x.mean(dim=2, keepdims=True).mean(dim=3, keepdims=True)
        # batch-size 1 bug/instabilities https://github.com/ultralytics/yolov5/issues/2891
        # beta = torch.sigmoid(self.bn2(self.fc2(self.bn1(self.fc1(y)))))  # bug/unstable
        beta = torch.sigmoid(self.fc2(self.fc1(y)))  # bug patch BN layers removed
        dpx = (self.p1 - self.p2) * x
        return dpx * torch.sigmoid(beta * dpx) + self.p2 * x

from utils.activations import MetaAconC
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
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        # 这里的nn.Identity()不改变input，直接return input
        # self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
        self.act = MetaAconC(c1=c2) 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)))

    # 前向加速推理模块
    # 用于Model类的fuse函数，融合conv+bn 加速推理 一般用于测试/验证阶段
    def forward_fuse(self, x):
        return self.act(self.conv(x))

# ---------------------------- CBAM start ---------------------------------

class ChannelAttention(nn.Module):
    def __init__(self, in_planes, ratio=16):
        super(ChannelAttention, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.max_pool = nn.AdaptiveMaxPool2d(1)
        # in_planes // ratio 这里会出现如下警告：
        # UserWarning: __floordiv__ is deprecated(被舍弃了), and its behavior will change in a future version of pytorch.
        # It currently rounds toward 0 (like the 'trunc' function NOT 'floor').
        # This results in incorrect rounding for negative values.
        # To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'),
        # or for actual floor division, use torch.div(a, b, rounding_mode='floor').
        # kernel = torch.DoubleTensor([*(x[0].shape[2:])]) // torch.DoubleTensor(list((m.output_size,))).squeeze()
        self.f1 = nn.Conv2d(in_planes, in_planes // ratio, 1, bias=False)
        self.relu = nn.ReLU()
        self.f2 = nn.Conv2d(in_planes // ratio, in_planes, 1, bias=False)
        # 写法二,亦可使用顺序容器
        # self.sharedMLP = nn.Sequential(
        # nn.Conv2d(in_planes, in_planes // ratio, 1, bias=False), nn.ReLU(),
        # nn.Conv2d(in_planes // rotio, in_planes, 1, bias=False))

    self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        # 全局平均池化—>MLP两层卷积
        avg_out = self.f2(self.relu(self.f1(self.avg_pool(x))))
        # 全局最大池化—>MLP两层卷积
        max_out = self.f2(self.relu(self.f1(self.max_pool(x))))
        out = self.sigmoid(avg_out + max_out)
        return out

class SpatialAttention(nn.Module):
    def __init__(self, kernel_size=7):
        super(SpatialAttention, self).__init__()

    assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
        padding = 3 if kernel_size == 7 else 1

    self.conv = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        # 基于channel的全局平均池化(channel=1)
        avg_out = torch.mean(x, dim=1, keepdim=True)
        # 基于channel的全局最大池化(channel=1)
        max_out, _ = torch.max(x, dim=1, keepdim=True)
        # channel拼接(channel=2)
        x = torch.cat([avg_out, max_out], dim=1)
        # channel=1
        x = self.conv(x)
        return self.sigmoid(x)

class CBAMBottleneck(nn.Module):
    # ch_in, ch_out, shortcut, groups, expansion, ratio, kernel_size
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, ratio=16, kernel_size=7):
        super(CBAMBottleneck, self).__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
        # 加入CBAM模块
        self.channel_attention = ChannelAttention(c2, ratio)
        self.spatial_attention = SpatialAttention(kernel_size)

    def forward(self, x):
        # 考虑加入CBAM模块的位置：bottleneck模块刚开始时、bottleneck模块中shortcut之前，这里选择在shortcut之前
        x2 = self.cv2(self.cv1(x))  # x和x2的channel数相同
        # 在bottleneck模块中shortcut之前加入CBAM模块
        out = self.channel_attention(x2) * x2
        # print('outchannels:{}'.format(out.shape))
        out = self.spatial_attention(out) * out
        return x + out if self.add else out

class C3CBAM(C3):
    # C3 module with CBAMBottleneck()
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__(c1, c2, n, shortcut, g, e)  # 引入C3(父类)的属性
        c_ = int(c2 * e)  # hidden channels
        self.m = nn.Sequential(*(CBAMBottleneck(c_, c_, shortcut) for _ in range(n)))

# ----------------------------- CBAM end ----------------------------------

# ----------------------------- CABlock start ----------------------------------

class h_sigmoid(nn.Module):
    def __init__(self, inplace=True):
        super(h_sigmoid, self).__init__()
        self.relu = nn.ReLU6(inplace=inplace)

    def forward(self, x):
        return self.relu(x + 3) / 6

class h_swish(nn.Module):
    def __init__(self, inplace=True):
        super(h_swish, self).__init__()
        self.sigmoid = h_sigmoid(inplace=inplace)

    def forward(self, x):
        return x * self.sigmoid(x)

class CABlock(nn.Module):
    def __init__(self, inp, oup, reduction=32):
        super(CABlock, self).__init__()
        # height方向上的均值池化
        self.pool_h = nn.AdaptiveAvgPool2d((None, 1))
        # width方向上的均值池化
        self.pool_w = nn.AdaptiveAvgPool2d((1, None))

    mip = max(8, inp // reduction)

    self.conv1 = nn.Conv2d(inp, mip, kernel_size=1, stride=1, padding=0)
        self.bn1 = nn.BatchNorm2d(mip)
        self.act = h_swish()

    self.conv_h = nn.Conv2d(mip, oup, kernel_size=1, stride=1, padding=0)
        self.conv_w = nn.Conv2d(mip, oup, kernel_size=1, stride=1, padding=0)

    def forward(self, x):
        identity = x

    n, c, h, w = x.size()
        x_h = self.pool_h(x)
        x_w = self.pool_w(x).permute(0, 1, 3, 2)

    y = torch.cat([x_h, x_w], dim=2)
        y = self.conv1(y)
        y = self.bn1(y)
        y = self.act(y)

    x_h, x_w = torch.split(y, [h, w], dim=2)
        x_w = x_w.permute(0, 1, 3, 2)

    a_h = self.conv_h(x_h).sigmoid()
        a_w = self.conv_w(x_w).sigmoid()

    out = identity * a_w * a_h

    return out

# ----------------------------- CABlock end ----------------------------------