Strip Pooling: Rethinking Spatial Pooling for Scene Parsing部分解釋

這個部分是：Strip pooling Module（SPM） 

SPM可以看做是一個Bottleneck部分，類似於residule

class SPBlock(nn.Module):
    def __init__(self, inplanes, outplanes, norm_layer=None):
        super(SPBlock, self).__init__()
        midplanes = outplanes
        self.conv1 = nn.Conv2d(inplanes, midplanes, kernel_size=(3, 1), padding=(1, 0), bias=False)
        self.bn1 = norm_layer(midplanes)
        self.conv2 = nn.Conv2d(inplanes, midplanes, kernel_size=(1, 3), padding=(0, 1), bias=False)
        self.bn2 = norm_layer(midplanes)
        self.conv3 = nn.Conv2d(midplanes, outplanes, kernel_size=1, bias=True)
        self.pool1 = nn.AdaptiveAvgPool2d((None, 1))
        self.pool2 = nn.AdaptiveAvgPool2d((1, None))
        self.relu = nn.ReLU(inplace=False)

    def forward(self, x):
        _, _, h, w = x.size()
        x1 = self.pool1(x)
        x1 = self.conv1(x1)
        x1 = self.bn1(x1)
        x1 = x1.expand(-1, -1, h, w)
        #x1 = F.interpolate(x1, (h, w))

        x2 = self.pool2(x)
        x2 = self.conv2(x2)
        x2 = self.bn2(x2)
        x2 = x2.expand(-1, -1, h, w)
        #x2 = F.interpolate(x2, (h, w))

        x = self.relu(x1 + x2)
        x = self.conv3(x).sigmoid()
        return x

MPM模塊，可以插入在Residule Modelu中減少參數 

class StripPooling(nn.Module):
    """
    Reference:
    """
    def __init__(self, in_channels, pool_size, norm_layer, up_kwargs):
        super(StripPooling, self).__init__()
        self.pool1 = nn.AdaptiveAvgPool2d(pool_size[0])
        self.pool2 = nn.AdaptiveAvgPool2d(pool_size[1])
        self.pool3 = nn.AdaptiveAvgPool2d((1, None))
        self.pool4 = nn.AdaptiveAvgPool2d((None, 1))

        inter_channels = int(in_channels/4)
        self.conv1_1 = nn.Sequential(nn.Conv2d(in_channels, inter_channels, 1, bias=False),
                                norm_layer(inter_channels),
                                nn.ReLU(True))
        self.conv1_2 = nn.Sequential(nn.Conv2d(in_channels, inter_channels, 1, bias=False),
                                norm_layer(inter_channels),
                                nn.ReLU(True))
        self.conv2_0 = nn.Sequential(nn.Conv2d(inter_channels, inter_channels, 3, 1, 1, bias=False),
                                norm_layer(inter_channels))
        self.conv2_1 = nn.Sequential(nn.Conv2d(inter_channels, inter_channels, 3, 1, 1, bias=False),
                                norm_layer(inter_channels))
        self.conv2_2 = nn.Sequential(nn.Conv2d(inter_channels, inter_channels, 3, 1, 1, bias=False),
                                norm_layer(inter_channels))
        self.conv2_3 = nn.Sequential(nn.Conv2d(inter_channels, inter_channels, (1, 3), 1, (0, 1), bias=False),
                                norm_layer(inter_channels))
        self.conv2_4 = nn.Sequential(nn.Conv2d(inter_channels, inter_channels, (3, 1), 1, (1, 0), bias=False),
                                norm_layer(inter_channels))
        self.conv2_5 = nn.Sequential(nn.Conv2d(inter_channels, inter_channels, 3, 1, 1, bias=False),
                                norm_layer(inter_channels),
                                nn.ReLU(True))
        self.conv2_6 = nn.Sequential(nn.Conv2d(inter_channels, inter_channels, 3, 1, 1, bias=False),
                                norm_layer(inter_channels),
                                nn.ReLU(True))
        self.conv3 = nn.Sequential(nn.Conv2d(inter_channels*2, in_channels, 1, bias=False),
                                norm_layer(in_channels))
        # bilinear interpolate options
        self._up_kwargs = up_kwargs

    def forward(self, x):
        _, _, h, w = x.size()
        x1 = self.conv1_1(x)
        x2 = self.conv1_2(x)
        x2_1 = self.conv2_0(x1)
        x2_2 = F.interpolate(self.conv2_1(self.pool1(x1)), (h, w), **self._up_kwargs)
        x2_3 = F.interpolate(self.conv2_2(self.pool2(x1)), (h, w), **self._up_kwargs)
        x2_4 = F.interpolate(self.conv2_3(self.pool3(x2)), (h, w), **self._up_kwargs)
        x2_5 = F.interpolate(self.conv2_4(self.pool4(x2)), (h, w), **self._up_kwargs)
        x1 = self.conv2_5(F.relu_(x2_1 + x2_2 + x2_3))
        x2 = self.conv2_6(F.relu_(x2_5 + x2_4))
        out = self.conv3(torch.cat([x1, x2], dim=1))
        return F.relu_(x + out)