Unet++代码
网络架构
黑色部分是Backbone，是原先的UNet。
绿色箭头为上采样，蓝色箭头为密集跳跃连接。
绿色的模块为密集连接块，是经过左边两个部分拼接操作后组成的
Backbone
2个3x3的卷积，padding=1。
class VGGBlock(nn.Module):
def __init__(self, in_channels, middle_channels, out_channels):
super().__init__()
self.relu = nn.ReLU(inplace=True)
self.conv1 = nn.Conv2d(in_channels, middle_channels, 3, padding=1)
self.bn1 = nn.BatchNorm2d(middle_channels)
self.conv2 = nn.Conv2d(middle_channels, out_channels, 3, padding=1)
self.bn2 = nn.BatchNorm2d(out_channels)
def forward(self, x):
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
return out
上采样
图中的绿色箭头，上采样使用双线性插值。
双线性插值就是有两个变量的插值函数的线性插值扩展，其核心思想是在两个方向分别进行一次线性插值
torch.nn.Upsample(size=None, scale_factor=None, mode='nearest', align_corners=None, recompute_scale_factor=None)
参数说明：
①size：可以用来指定输出空间的大小，默认是None；
②scale_factor：比例因子，比如scale_factor=2意味着将输入图像上采样2倍，默认是None；
③mode：用来指定上采样算法，有’nearest’、 ‘linear’、‘bilinear’、‘bicubic’、‘trilinear’，默认是’nearest’。上采样算法在本文中会有详细理论进行讲解；
④align_corners：如果True，输入和输出张量的角像素对齐，从而保留这些像素的值，默认是False。此处True和False的区别本文中会有详细的理论讲解；
⑤recompute_scale_factor：如果recompute_scale_factor是True，则必须传入scale_factor并且scale_factor用于计算输出大小。计算出的输出大小将用于推断插值的新比例。请注意，当scale_factor为浮点数时，由于舍入和精度问题，它可能与重新计算的scale_factor不同。如果recompute_scale_factor是False，那么size或scale_factor将直接用于插值。
class Up(nn.Module):
def __init__(self):
super().__init__()
self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
def forward(self, x1, x2):
x1 = self.up(x1)
# input is CHW
diffY = torch.tensor([x2.size()[2] - x1.size()[2]])
diffX = torch.tensor([x2.size()[3] - x1.size()[3]])
x1 = F.pad(x1, [diffX // 2, diffX - diffX // 2,
diffY // 2, diffY - diffY // 2])
x = torch.cat([x2, x1], dim=1)
return x
下采样
图中的黑色箭头，采用的是最大池化。
self.pool = nn.MaxPool2d(2, 2)
深度监督
所示，该结构下有4个分支，可以分为两种模式。
精确模式：4个分支取平均值结果
快速模式：只选择一个分支，其余被剪枝
if self.deep_supervision:
output1 = self.final1(x0_1)
output2 = self.final2(x0_2)
output3 = self.final3(x0_3)
output4 = self.final4(x0_4)
return [output1, output2, output3, output4]
else:
output = self.final(x0_4)
return output
网络架构代码
class NestedUNet(nn.Module):
def __init__(self, num_classes=1, input_channels=1, deep_supervision=False, **kwargs):
super().__init__()
nb_filter = [32, 64, 128, 256, 512]
self.deep_supervision = deep_supervision
self.pool = nn.MaxPool2d(2, 2)
self.up = Up()
self.conv0_0 = VGGBlock(input_channels, nb_filter[0], nb_filter[0])
self.conv1_0 = VGGBlock(nb_filter[0], nb_filter[1], nb_filter[1])
self.conv2_0 = VGGBlock(nb_filter[1], nb_filter[2], nb_filter[2])
self.conv3_0 = VGGBlock(nb_filter[2], nb_filter[3], nb_filter[3])
self.conv4_0 = VGGBlock(nb_filter[3], nb_filter[4], nb_filter[4])
self.conv0_1 = VGGBlock(nb_filter[0]+nb_filter[1], nb_filter[0], nb_filter[0])
self.conv1_1 = VGGBlock(nb_filter[1]+nb_filter[2], nb_filter[1], nb_filter[1])
self.conv2_1 = VGGBlock(nb_filter[2]+nb_filter[3], nb_filter[2], nb_filter[2])
self.conv3_1 = VGGBlock(nb_filter[3]+nb_filter[4], nb_filter[3], nb_filter[3])
self.conv0_2 = VGGBlock(nb_filter[0]*2+nb_filter[1], nb_filter[0], nb_filter[0])
self.conv1_2 = VGGBlock(nb_filter[1]*2+nb_filter[2], nb_filter[1], nb_filter[1])
self.conv2_2 = VGGBlock(nb_filter[2]*2+nb_filter[3], nb_filter[2], nb_filter[2])
self.conv0_3 = VGGBlock(nb_filter[0]*3+nb_filter[1], nb_filter[0], nb_filter[0])
self.conv1_3 = VGGBlock(nb_filter[1]*3+nb_filter[2], nb_filter[1], nb_filter[1])
self.conv0_4 = VGGBlock(nb_filter[0]*4+nb_filter[1], nb_filter[0], nb_filter[0])
if self.deep_supervision:
self.final1 = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
self.final2 = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
self.final3 = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
self.final4 = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
else:
self.final = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
def forward(self, input):
x0_0 = self.conv0_0(input)
x1_0 = self.conv1_0(self.pool(x0_0))
x0_1 = self.conv0_1(self.up(x1_0, x0_0))
x2_0 = self.conv2_0(self.pool(x1_0))
x1_1 = self.conv1_1(self.up(x2_0, x1_0))
x0_2 = self.conv0_2(self.up(x1_1, torch.cat([x0_0, x0_1], 1)))
x3_0 = self.conv3_0(self.pool(x2_0))
x2_1 = self.conv2_1(self.up(x3_0, x2_0))
x1_2 = self.conv1_2(self.up(x2_1, torch.cat([x1_0, x1_1], 1)))
x0_3 = self.conv0_3(self.up(x1_2, torch.cat([x0_0, x0_1, x0_2], 1)))
x4_0 = self.conv4_0(self.pool(x3_0))
x3_1 = self.conv3_1(self.up(x4_0, x3_0))
x2_2 = self.conv2_2(self.up(x3_1, torch.cat([x2_0, x2_1], 1)))
x1_3 = self.conv1_3(self.up(x2_2, torch.cat([x1_0, x1_1, x1_2], 1)))
x0_4 = self.conv0_4(self.up(x1_3, torch.cat([x0_0, x0_1, x0_2, x0_3], 1)))
if self.deep_supervision:
output1 = self.final1(x0_1)
output2 = self.final2(x0_2)
output3 = self.final3(x0_3)
output4 = self.final4(x0_4)
return [output1, output2, output3, output4]
else:
output = self.final(x0_4)
return output