GhostNet: More Features from Cheap Operations

GhostNet: More Features from Cheap Operations

一. 论文简介

论文可视化特征图如下所示，目的是找到更多的特征对(Ghost)

如何找到？

论文意思是保留内在特征(instrinsic feature)，可以获得更多的特征对

如何判定？

未解释

二. 模块详解

2.1 整体结构介绍

1. Ghost module

先进行正常卷积(代码用的1*1降低计算量)，然后分组卷积，最后将输入特征和输出特征concat即可，关于卷积的一些操作如下链接所示：Point-wise / Depth-wise / group-convolution / Global Depthwise Convolution / Global Average Pooling

class GhostModule(nn.Module):
    def __init__(self, inp, oup, kernel_size=1, ratio=2, dw_size=3, stride=1, relu=True):
        super(GhostModule, self).__init__()
        self.oup = oup
        init_channels = math.ceil(oup / ratio)
        new_channels = init_channels*(ratio-1)
        # Custom Convolution
        self.primary_conv = nn.Sequential(
            nn.Conv2d(inp, init_channels, kernel_size, stride, kernel_size//2, bias=False),
            nn.BatchNorm2d(init_channels),
            nn.ReLU(inplace=True) if relu else nn.Sequential(),
        )
        # Depth-wise  Convolution
        self.cheap_operation = nn.Sequential(
            nn.Conv2d(init_channels, new_channels, dw_size, 1, dw_size//2, groups=init_channels, bias=False),
            nn.BatchNorm2d(new_channels),
            nn.ReLU(inplace=True) if relu else nn.Sequential(),
        )

    def forward(self, x):
        x1 = self.primary_conv(x)
        x2 = self.cheap_operation(x1)
        out = torch.cat([x1,x2], dim=1)
        return out[:,:self.oup,:,:]

2. GhostBottleneck

就是将Ghost module加入到resnet之内即可

class GhostBottleneck(nn.Module):
    """ Ghost bottleneck w/ optional SE"""

    def __init__(self, in_chs, mid_chs, out_chs, dw_kernel_size=3,
                 stride=1, act_layer=nn.ReLU, se_ratio=0.):
        super(GhostBottleneck, self).__init__()
        has_se = se_ratio is not None and se_ratio > 0.
        self.stride = stride

        # Point-wise expansion
        self.ghost1 = GhostModule(in_chs, mid_chs, relu=True)

        # Depth-wise convolution
        if self.stride > 1:
            self.conv_dw = nn.Conv2d(mid_chs, mid_chs, dw_kernel_size, stride=stride,
                             padding=(dw_kernel_size-1)//2,
                             groups=mid_chs, bias=False)
            self.bn_dw = nn.BatchNorm2d(mid_chs)

        # Squeeze-and-excitation
        if has_se:
            self.se = SqueezeExcite(mid_chs, se_ratio=se_ratio)
        else:
            self.se = None

        # Point-wise linear projection
        self.ghost2 = GhostModule(mid_chs, out_chs, relu=False)
        
        # shortcut
        if (in_chs == out_chs and self.stride == 1):
            self.shortcut = nn.Sequential()
        else:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_chs, in_chs, dw_kernel_size, stride=stride,
                       padding=(dw_kernel_size-1)//2, groups=in_chs, bias=False),
                nn.BatchNorm2d(in_chs),
                nn.Conv2d(in_chs, out_chs, 1, stride=1, padding=0, bias=False),
                nn.BatchNorm2d(out_chs),
            )


    def forward(self, x):
        residual = x

        # 1st ghost bottleneck
        x = self.ghost1(x)

        # Depth-wise convolution
        if self.stride > 1:
            x = self.conv_dw(x)
            x = self.bn_dw(x)

        # Squeeze-and-excitation
        if self.se is not None:
            x = self.se(x)

        # 2nd ghost bottleneck
        x = self.ghost2(x)
        
        x += self.shortcut(residual)
        return x

3. SE模块

Attention mode，通道使用不同权重

https://arxiv.org/abs/1709.01507

# SE module that attetion mode
class SqueezeExcite(nn.Module):
    def __init__(self, in_chs, se_ratio=0.25, reduced_base_chs=None,
                 act_layer=nn.ReLU, gate_fn=hard_sigmoid, divisor=4, **_):
        super(SqueezeExcite, self).__init__()
        self.gate_fn = gate_fn
        reduced_chs = _make_divisible((reduced_base_chs or in_chs) * se_ratio, divisor)
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.conv_reduce = nn.Conv2d(in_chs, reduced_chs, 1, bias=True)
        self.act1 = act_layer(inplace=True)
        self.conv_expand = nn.Conv2d(reduced_chs, in_chs, 1, bias=True)

    def forward(self, x):
        x_se = self.avg_pool(x)
        x_se = self.conv_reduce(x_se)
        x_se = self.act1(x_se)
        x_se = self.conv_expand(x_se)
        x = x * self.gate_fn(x_se)
        return x