文章摘要
这篇文章介绍了名为**NestedUNet**的深度学习模型，该模型基于UNet架构，用于图像分割任务。其核心特点包括多尺度特征融合和多级分类机制。模型通过多层级的卷积块（VGGBlock）提取特征，并在每个层级使用上采样模块（Up）进行特征重建。文章还提到该模型支持**深监督**（deep supervision），即在多个层级输出分割结果，提升模型性能。整体来看，NestedUNet通过多层次特征融合和多级分类，有效解决了传统UNet在复杂场景下的分割问题。
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