这个部分是:Strip pooling Module(SPM)
SPM可以看做是一个Bottleneck部分,类似于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模块,可以插入在Residule Modelu中减少参数
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)