【医学图像分割网络】之U-Net网络PyTorch复现
【医学图像分割网络】之U-Net网络PyTorch复现
1.内容
U-Net网络算是医学图像分割领域的开山之作，我接触深度学习到现在大概将近大半年时间，看到了很多基于U-Net网络的变体，后续也会继续和大家一起分享学习。我现在正常拿到一个分割任务时，都是先拿U-Net网络进行测试，一般U-Net跑出的模型精度是非常高的，虽说论文出的早，但是确实经典，在很多分割任务上表现不俗，优点和网络结构就不谈了，很多博客都有详细的介绍，论文也说的很清楚，这里直接上代码。
这里提出的是，很多博客都不是按照原始作者论文里的网络结构，比如在卷积的padding，跳层连接的尺寸上都做了一定的修改，虽然这样更适合多种数据的训练，更加使用，但是对于我们学会复现原始结构造成了障碍，这里我分享出两种，一种是原始论文的，一种是更加通用的。
2.论文原始版U-Net实现方式
"""
论文原始版U-Net
"""
import torch
from torch import nn
import torch.nn.functional as F
from torchsummary import summary
from collections import OrderedDict
# 编码连续卷积层
def contracting_block(in_channels, out_channels):
block = torch.nn.Sequential(
nn.Conv2d(kernel_size=(3, 3), in_channels=in_channels, out_channels=out_channels),
nn.ReLU(),
nn.BatchNorm2d(out_channels),
nn.Conv2d(kernel_size=(3, 3), in_channels=out_channels, out_channels=out_channels),
nn.ReLU(),
nn.BatchNorm2d(out_channels)
)
return block
# 解码上采样卷积层
class expansive_block(nn.Module):
def __init__(self, in_channels, mid_channels, out_channels):
super(expansive_block, self).__init__()
self.up = nn.ConvTranspose2d(in_channels, in_channels // 2, kernel_size=(3, 3), stride=2, padding=1,
output_padding=1, dilation=1)
self.block = nn.Sequential(
nn.Conv2d(kernel_size=(3, 3), in_channels=in_channels, out_channels=mid_channels),
nn.ReLU(),
nn.BatchNorm2d(mid_channels),
nn.Conv2d(kernel_size=(3, 3), in_channels=mid_channels, out_channels=out_channels),
nn.ReLU(),
nn.BatchNorm2d(out_channels)
)
def forward(self, e, d):
d = self.up(d)
# concat
diffY = e.size()[2] - d.size()[2]
diffX = e.size()[3] - d.size()[3]
e = e[:, :, diffY // 2:e.size()[2] - diffY // 2, diffX // 2:e.size()[3] - diffX // 2]
cat = torch.cat([e, d], dim=1)
out = self.block(cat)
return out
# 输出层
def final_block(in_channels, out_channels):
block = nn.Sequential(
nn.Conv2d(kernel_size=(1, 1), in_channels=in_channels, out_channels=out_channels),
nn.ReLU(),
nn.BatchNorm2d(out_channels),
)
return block
# U-Net
class Unet(nn.Module):
def __init__(self, in_channel, out_channel):
super(Unet, self).__init__()
# Encode
self.conv_encode1 = contracting_block(in_channels=in_channel, out_channels=64)
self.conv_pool1 = nn.MaxPool2d(kernel_size=2, stride=2)
self.conv_encode2 = contracting_block(in_channels=64, out_channels=128)
self.conv_pool2 = nn.MaxPool2d(kernel_size=2, stride=2)
self.conv_encode3 = contracting_block(in_channels=128, out_channels=256)
self.conv_pool3 = nn.MaxPool2d(kernel_size=2, stride=2)
self.conv_encode4 = contracting_block(in_channels=256, out_channels=512)
self.conv_pool4 = nn.MaxPool2d(kernel_size=2, stride=2)
# Bottleneck
self.bottleneck = torch.nn.Sequential(
nn.Conv2d(kernel_size=3, in_channels=512, out_channels=1024),
nn.ReLU(),
nn.BatchNorm2d(1024),
nn.Conv2d(kernel_size=3, in_channels=1024, out_channels=1024),
nn.ReLU(),
nn.BatchNorm2d(1024)
)
# Decode
self.conv_decode4 = expansive_block(1024, 512, 512)
self.conv_decode3 = expansive_block(512, 256, 256)
self.conv_decode2 = expansive_block(256, 128, 128)
self.conv_decode1 = expansive_block(128, 64, 64)
self.final_layer = final_block(64, out_channel)
def forward(self, x):
# set_trace()
# Encode
encode_block1 = self.conv_encode1(x)
encode_pool1 = self.conv_pool1(encode_block1)
encode_block2 = self.conv_encode2(encode_pool1)
encode_pool2 = self.conv_pool2(encode_block2)
encode_block3 = self.conv_encode3(encode_pool2)
encode_pool3 = self.conv_pool3(encode_block3)
encode_block4 = self.conv_encode4(encode_pool3)
encode_pool4 = self.conv_pool4(encode_block4)
# Bottleneck
bottleneck = self.bottleneck(encode_pool4)
# Decode
decode_block4 = self.conv_decode4(encode_block4, bottleneck)
decode_block3 = self.conv_decode3(encode_block3, decode_block4)
decode_block2 = self.conv_decode2(encode_block2, decode_block3)
decode_block1 = self.conv_decode1(encode_block1, decode_block2)
final_layer = self.final_layer(decode_block1)
return final_layer3.实际通用版U-Net实现方式1
"""
实用版U-Net
"""
class DoubleConv(nn.Module):
def __init__(self, in_ch, out_ch):
super(DoubleConv, self).__init__()
self.conv = nn.Sequential(
nn.Conv2d(in_ch, out_ch, 3, padding=1),
nn.BatchNorm2d(out_ch),
nn.ReLU(inplace=True),
nn.Conv2d(out_ch, out_ch, 3, padding=1),
nn.BatchNorm2d(out_ch),
nn.ReLU(inplace=True)
)
def forward(self, input):
return self.conv(input)
class Unet2(nn.Module):
def __init__(self, in_ch, out_ch):
super(Unet2, self).__init__()
self.conv1 = DoubleConv(in_ch, 32)
self.pool1 = nn.MaxPool2d(2)
self.conv2 = DoubleConv(32, 64)
self.pool2 = nn.MaxPool2d(2)
self.conv3 = DoubleConv(64, 128)
self.pool3 = nn.MaxPool2d(2)
self.conv4 = DoubleConv(128, 256)
self.pool4 = nn.MaxPool2d(2)
self.conv5 = DoubleConv(256, 512)
self.up6 = nn.ConvTranspose2d(512, 256, 2, stride=2)
self.conv6 = DoubleConv(512, 256)
self.up7 = nn.ConvTranspose2d(256, 128, 2, stride=2)
self.conv7 = DoubleConv(256, 128)
self.up8 = nn.ConvTranspose2d(128, 64, 2, stride=2)
self.conv8 = DoubleConv(128, 64)
self.up9 = nn.ConvTranspose2d(64, 32, 2, stride=2)
self.conv9 = DoubleConv(64, 32)
self.conv10 = nn.Conv2d(32, out_ch, 1)
def forward(self, x):
c1 = self.conv1(x)
p1 = self.pool1(c1)
c2 = self.conv2(p1)
p2 = self.pool2(c2)
c3 = self.conv3(p2)
p3 = self.pool3(c3)
c4 = self.conv4(p3)
p4 = self.pool4(c4)
c5 = self.conv5(p4)
up_6 = self.up6(c5)
merge6 = torch.cat([up_6, c4], dim=1)
c6 = self.conv6(merge6)
up_7 = self.up7(c6)
merge7 = torch.cat([up_7, c3], dim=1)
c7 = self.conv7(merge7)
up_8 = self.up8(c7)
merge8 = torch.cat([up_8, c2], dim=1)
c8 = self.conv8(merge8)
up_9 = self.up9(c8)
merge9 = torch.cat([up_9, c1], dim=1)
c9 = self.conv9(merge9)
c10 = self.conv10(c9)
out = nn.Sigmoid()(c10)
return out
4.实际通用版U-Net实现方式2
"""
实用版U-Net2
"""
class Unet3(nn.Module):
def __init__(self, in_channels=3, out_channels=1, init_features=32):
super(Unet3, self).__init__()
features = init_features
self.encoder1 = Unet3._block(in_channels, features, name="enc1")
self.pool1 = nn.MaxPool2d(kernel_size=2, stride=2)
self.encoder2 = Unet3._block(features, features * 2, name="enc2")
self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2)
self.encoder3 = Unet3._block(features * 2, features * 4, name="enc3")
self.pool3 = nn.MaxPool2d(kernel_size=2, stride=2)
self.encoder4 = Unet3._block(features * 4, features * 8, name="enc4")
self.pool4 = nn.MaxPool2d(kernel_size=2, stride=2)
self.bottleneck = Unet3._block(features * 8, features * 16, name="bottleneck")
self.upconv4 = nn.ConvTranspose2d(
features * 16, features * 8, kernel_size=2, stride=2
)
self.decoder4 = Unet3._block((features * 8) * 2, features * 8, name="dec4")
self.upconv3 = nn.ConvTranspose2d(
features * 8, features * 4, kernel_size=2, stride=2
)
self.decoder3 = Unet3._block((features * 4) * 2, features * 4, name="dec3")
self.upconv2 = nn.ConvTranspose2d(
features * 4, features * 2, kernel_size=2, stride=2
)
self.decoder2 = Unet3._block((features * 2) * 2, features * 2, name="dec2")
self.upconv1 = nn.ConvTranspose2d(
features * 2, features, kernel_size=2, stride=2
)
self.decoder1 = Unet3._block(features * 2, features, name="dec1")
self.conv = nn.Conv2d(
in_channels=features, out_channels=out_channels, kernel_size=1
)
def forward(self, x):
enc1 = self.encoder1(x)
enc2 = self.encoder2(self.pool1(enc1))
enc3 = self.encoder3(self.pool2(enc2))
enc4 = self.encoder4(self.pool3(enc3))
bottleneck = self.bottleneck(self.pool4(enc4))
dec4 = self.upconv4(bottleneck)
dec4 = torch.cat((dec4, enc4), dim=1)
dec4 = self.decoder4(dec4)
dec3 = self.upconv3(dec4)
dec3 = torch.cat((dec3, enc3), dim=1)
dec3 = self.decoder3(dec3)
dec2 = self.upconv2(dec3)
dec2 = torch.cat((dec2, enc2), dim=1)
dec2 = self.decoder2(dec2)
dec1 = self.upconv1(dec2)
dec1 = torch.cat((dec1, enc1), dim=1)
dec1 = self.decoder1(dec1)
return torch.sigmoid(self.conv(dec1))
@staticmethod
def _block(in_channels, features, name):
return nn.Sequential(
OrderedDict(
[
(
name + "conv1",
nn.Conv2d(
in_channels=in_channels,
out_channels=features,
kernel_size=3,
padding=1,
bias=False,
),
),
(name + "norm1", nn.BatchNorm2d(num_features=features)),
(name + "relu1", nn.ReLU(inplace=True)),
(
name + "conv2",
nn.Conv2d(
in_channels=features,
out_channels=features,
kernel_size=3,
padding=1,
bias=False,
),
),
(name + "norm2", nn.BatchNorm2d(num_features=features)),
(name + "relu2", nn.ReLU(inplace=True)),
]
)
)