UNet和U2Net都是语义分割领域中的深度学习模型
UNet是一种用于图像分割的深度学习模型,由Olaf Ronneberger等人在2015年提出
具有一种特殊的U形结构,可以将输入图像逐步缩小,然后再将其逐步放大,以产生分割结果。
UNet在医学图像分割、自然图像分割等领域具有广泛的应用
U2Net是由Ningning Wang等人在2020年提出的一种语义分割网络,可以高效地提取图像中的边缘和细节信息。
相对于UNet,U2Net采用了更深的网络结构,并引入了一个新的Attention U-Net模块,以更好地保留图像中的细节信息。
UNet
import torch
import torch.nn as nn
import torch.nn.functional as F
class CNN_Block(nn.Module):
def __init__(self, c_in, c_out):
super().__init__()
self.layer = nn.Sequential(
# 不改变特征的HW,改变特征的C
# 完成了CHW层面的像素融合
nn.Conv2d(in_channels=c_in, out_channels=c_out, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(c_out),
nn.LeakyReLU(),
# nn.Dropout(0.2)
nn.Conv2d(in_channels=c_out, out_channels=c_out, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(c_out),
nn.LeakyReLU(),
# nn.Dropout(0.2)
)
def forward(self, x):
return self.layer(x)
# 下采样,/2,C不变。
class DownSample_Block(nn.Module):
def __init__(self, c):
super().__init__()
self.layer = nn.Sequential(
nn.MaxPool2d(2),
CNN_Block(c, c)
)
def forward(self, x):
return self.layer(x)
# 上采样,*2,C减半
class UpSample_Block(nn.Module):
def __init__(self, c):
super().__init__()
self.layer = nn.Sequential(
nn.Conv2d(in_channels=c, out_channels=c // 2, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(c // 2),
nn.LeakyReLU(),
# nn.Dropout(0.2)
)
# x:o5 r:o4
# x:o6 r:o3
# x:o7 r:o2
# x:o8 r:o1
def forward(self, x, r):
# 先把HW * 2,再把C / 2
data = F.interpolate(x, scale_factor=2, mode="nearest")
data = self.layer(data)
# 信息补全
return torch.cat((data, r), dim=1)
class UNet(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = CNN_Block(3, 64)
self.down1 = DownSample_Block(64)
self.conv2 = CNN_Block(64, 128)
self.down2 = DownSample_Block(128)
self.conv3 = CNN_Block(128, 256)
self.down3 = DownSample_Block(256)
self.conv4 = CNN_Block(256, 512)
self.down4 = DownSample_Block(512)
self.conv5 = CNN_Block(512, 1024)
self.up1 = UpSample_Block(1024)
#
self.conv6 = CNN_Block(1024, 512)
self.up2 = UpSample_Block(512)
self.conv7 = CNN_Block(512, 256)
self.up3 = UpSample_Block(256)
self.conv8 = CNN_Block(256, 128)
self.up4 = UpSample_Block(128)
self.conv9 = CNN_Block(128, 64)
# 输出层
self.out_layer = nn.Conv2d(64, 1, 1, 1)
def forward(self, x):
o1 = self.conv1(x)
o2 = self.conv2(self.down1(o1))
o3 = self.conv3(self.down2(o2))
o4 = self.conv4(self.down3(o3))
o5 = self.conv5(self.down4(o4))
# 信息补全
# x:o5 r:o4
# x:o6 r:o3
# x:o7 r:o2
# x:o8 r:o1
o6 = self.conv6(self.up1(o5, o4))
o7 = self.conv7(self.up2(o6, o3))
o8 = self.conv8(self.up3(o7, o2))
o9 = self.conv9(self.up4(o8, o1))
return self.out_layer(o9)
# if __name__ == '__main__':
# data = torch.randn(1, 3, 256, 256)
# unet = UNet()
# data = unet(data)
# print(data.shape)
U2Net
import torch
import torch.nn as nn
import torch.nn.functional as F
class REBNCONV(nn.Module):
def __init__(self, in_ch=3, out_ch=3, dirate=1):
super(REBNCONV, self).__init__()
# 卷积核为3的情况下,padding == dilation,输出HW不变
self.conv_s1 = nn.Conv2d(in_ch, out_ch, 3, padding=1 * dirate, dilation=1 * dirate)
self.bn_s1 = nn.BatchNorm2d(out_ch)
self.relu_s1 = nn.ReLU(inplace=True)
def forward(self, x):
hx = x
xout = self.relu_s1(self.bn_s1(self.conv_s1(hx)))
return xout
## upsample tensor 'src' to have the same spatial size with tensor 'tar'
def _upsample_like(src, tar):
# src = F.interpolate(src, size=tar.shape[2:], mode='bilinear') # old version torch
# tar:NCHW
src = F.interpolate(src, size=tar.shape[2:], mode='bilinear', align_corners=True)
return src
### RSU-7 ###
class RSU7(nn.Module): # UNet07DRES(nn.Module):
def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
super(RSU7, self).__init__()
self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1)
self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1)
self.pool3 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1)
self.pool4 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=1)
self.pool5 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.rebnconv6 = REBNCONV(mid_ch, mid_ch, dirate=1)
self.rebnconv7 = REBNCONV(mid_ch, mid_ch, dirate=2)
self.rebnconv6d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
self.rebnconv5d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1)
def forward(self, x):
hx = x
hxin = self.rebnconvin(hx)
hx1 = self.rebnconv1(hxin)
hx = self.pool1(hx1)
hx2 = self.rebnconv2(hx)
hx = self.pool2(hx2)
hx3 = self.rebnconv3(hx)
hx = self.pool3(hx3)
hx4 = self.rebnconv4(hx)
hx = self.pool4(hx4)
hx5 = self.rebnconv5(hx)
hx = self.pool5(hx5)
hx6 = self.rebnconv6(hx)
hx7 = self.rebnconv7(hx6)
hx6d = self.rebnconv6d(torch.cat((hx7, hx6), 1))
hx6dup = _upsample_like(hx6d, hx5)
hx5d = self.rebnconv5d(torch.cat((hx6dup, hx5), 1))
hx5dup = _upsample_like(hx5d, hx4)
hx4d = self.rebnconv4d(torch.cat((hx5dup, hx4), 1))
hx4dup = _upsample_like(hx4d, hx3)
hx3d = self.rebnconv3d(torch.cat((hx4dup, hx3), 1))
hx3dup = _upsample_like(hx3d, hx2)
hx2d = self.rebnconv2d(torch.cat((hx3dup, hx2), 1))
hx2dup = _upsample_like(hx2d, hx1)
hx1d = self.rebnconv1d(torch.cat((hx2dup, hx1), 1))
return hx1d + hxin
### RSU-6 ###
class RSU6(nn.Module): # UNet06DRES(nn.Module):
def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
super(RSU6, self).__init__()
self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1)
self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1)
self.pool3 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1)
self.pool4 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=1)
self.rebnconv6 = REBNCONV(mid_ch, mid_ch, dirate=2)
self.rebnconv5d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1)
def forward(self, x):
hx = x
hxin = self.rebnconvin(hx)
hx1 = self.rebnconv1(hxin)
hx = self.pool1(hx1)
hx2 = self.rebnconv2(hx)
hx = self.pool2(hx2)
hx3 = self.rebnconv3(hx)
hx = self.pool3(hx3)
hx4 = self.rebnconv4(hx)
hx = self.pool4(hx4)
hx5 = self.rebnconv5(hx)
hx6 = self.rebnconv6(hx5)
hx5d = self.rebnconv5d(torch.cat((hx6, hx5), 1))
hx5dup = _upsample_like(hx5d, hx4)
hx4d = self.rebnconv4d(torch.cat((hx5dup, hx4), 1))
hx4dup = _upsample_like(hx4d, hx3)
hx3d = self.rebnconv3d(torch.cat((hx4dup, hx3), 1))
hx3dup = _upsample_like(hx3d, hx2)
hx2d = self.rebnconv2d(torch.cat((hx3dup, hx2), 1))
hx2dup = _upsample_like(hx2d, hx1)
hx1d = self.rebnconv1d(torch.cat((hx2dup, hx1), 1))
return hx1d + hxin
### RSU-5 ###
class RSU5(nn.Module): # UNet05DRES(nn.Module):
def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
super(RSU5, self).__init__()
self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1)
self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1)
self.pool3 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1)
self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=2)
self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1)
def forward(self, x):
hx = x
hxin = self.rebnconvin(hx)
hx1 = self.rebnconv1(hxin)
hx = self.pool1(hx1)
hx2 = self.rebnconv2(hx)
hx = self.pool2(hx2)
hx3 = self.rebnconv3(hx)
hx = self.pool3(hx3)
hx4 = self.rebnconv4(hx)
hx5 = self.rebnconv5(hx4)
hx4d = self.rebnconv4d(torch.cat((hx5, hx4), 1))
hx4dup = _upsample_like(hx4d, hx3)
hx3d = self.rebnconv3d(torch.cat((hx4dup, hx3), 1))
hx3dup = _upsample_like(hx3d, hx2)
hx2d = self.rebnconv2d(torch.cat((hx3dup, hx2), 1))
hx2dup = _upsample_like(hx2d, hx1)
hx1d = self.rebnconv1d(torch.cat((hx2dup, hx1), 1))
return hx1d + hxin
### RSU-4 ###
class RSU4(nn.Module): # UNet04DRES(nn.Module):
def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
super(RSU4, self).__init__()
self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1)
self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1)
self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=2)
self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1)
self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1)
def forward(self, x):
hx = x
hxin = self.rebnconvin(hx)
hx1 = self.rebnconv1(hxin)
hx = self.pool1(hx1)
hx2 = self.rebnconv2(hx)
hx = self.pool2(hx2)
hx3 = self.rebnconv3(hx)
hx4 = self.rebnconv4(hx3)
hx3d = self.rebnconv3d(torch.cat((hx4, hx3), 1))
hx3dup = _upsample_like(hx3d, hx2)
hx2d = self.rebnconv2d(torch.cat((hx3dup, hx2), 1))
hx2dup = _upsample_like(hx2d, hx1)
hx1d = self.rebnconv1d(torch.cat((hx2dup, hx1), 1))
return hx1d + hxin
### RSU-4F ###
class RSU4F(nn.Module): # UNet04FRES(nn.Module):
def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
super(RSU4F, self).__init__()
self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=2)
self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=4)
self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=8)
self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=4)
self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=2)
self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1)
def forward(self, x):
hx = x
hxin = self.rebnconvin(hx)
hx1 = self.rebnconv1(hxin)
hx2 = self.rebnconv2(hx1)
hx3 = self.rebnconv3(hx2)
hx4 = self.rebnconv4(hx3)
hx3d = self.rebnconv3d(torch.cat((hx4, hx3), 1))
hx2d = self.rebnconv2d(torch.cat((hx3d, hx2), 1))
hx1d = self.rebnconv1d(torch.cat((hx2d, hx1), 1))
return hx1d + hxin
##### U^2-Net ####
class U2NET(nn.Module):
def __init__(self, in_ch=3, out_ch=1):
super(U2NET, self).__init__()
# encoder
self.stage1 = RSU7(in_ch, 32, 64)
self.pool12 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.stage2 = RSU6(64, 32, 128)
self.pool23 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.stage3 = RSU5(128, 64, 256)
self.pool34 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.stage4 = RSU4(256, 128, 512)
self.pool45 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.stage5 = RSU4F(512, 256, 512)
self.pool56 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.stage6 = RSU4F(512, 256, 512)
# decoder
self.stage5d = RSU4F(1024, 256, 512)
self.stage4d = RSU4(1024, 128, 256)
self.stage3d = RSU5(512, 64, 128)
self.stage2d = RSU6(256, 32, 64)
self.stage1d = RSU7(128, 16, 64)
self.side1 = nn.Conv2d(64, out_ch, 3, padding=1)
self.side2 = nn.Conv2d(64, out_ch, 3, padding=1)
self.side3 = nn.Conv2d(128, out_ch, 3, padding=1)
self.side4 = nn.Conv2d(256, out_ch, 3, padding=1)
self.side5 = nn.Conv2d(512, out_ch, 3, padding=1)
self.side6 = nn.Conv2d(512, out_ch, 3, padding=1)
self.outconv = nn.Conv2d(6 * out_ch, out_ch, 1)
def forward(self, x):
hx = x
# stage 1
hx1 = self.stage1(hx)
hx = self.pool12(hx1)
# stage 2
hx2 = self.stage2(hx)
hx = self.pool23(hx2)
# stage 3
hx3 = self.stage3(hx)
hx = self.pool34(hx3)
# stage 4
hx4 = self.stage4(hx)
hx = self.pool45(hx4)
# stage 5
hx5 = self.stage5(hx)
hx = self.pool56(hx5)
# stage 6
hx6 = self.stage6(hx)
hx6up = _upsample_like(hx6, hx5)
# -------------------- decoder --------------------
hx5d = self.stage5d(torch.cat((hx6up, hx5), 1))
hx5dup = _upsample_like(hx5d, hx4)
hx4d = self.stage4d(torch.cat((hx5dup, hx4), 1))
hx4dup = _upsample_like(hx4d, hx3)
hx3d = self.stage3d(torch.cat((hx4dup, hx3), 1))
hx3dup = _upsample_like(hx3d, hx2)
hx2d = self.stage2d(torch.cat((hx3dup, hx2), 1))
hx2dup = _upsample_like(hx2d, hx1)
hx1d = self.stage1d(torch.cat((hx2dup, hx1), 1))
# side output
d1 = self.side1(hx1d)
d2 = self.side2(hx2d)
d2 = _upsample_like(d2, d1)
d3 = self.side3(hx3d)
d3 = _upsample_like(d3, d1)
d4 = self.side4(hx4d)
d4 = _upsample_like(d4, d1)
d5 = self.side5(hx5d)
d5 = _upsample_like(d5, d1)
d6 = self.side6(hx6)
d6 = _upsample_like(d6, d1)
d0 = self.outconv(torch.cat((d1, d2, d3, d4, d5, d6), 1))
return torch.sigmoid(d0), torch.sigmoid(d1), torch.sigmoid(d2), torch.sigmoid(d3), torch.sigmoid(
d4), torch.sigmoid(d5), torch.sigmoid(d6)
### U^2-Net small ###
class U2NETP(nn.Module):
def __init__(self, in_ch=3, out_ch=1):
super(U2NETP, self).__init__()
self.stage1 = RSU7(in_ch, 16, 64)
self.pool12 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.stage2 = RSU6(64, 16, 64)
self.pool23 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.stage3 = RSU5(64, 16, 64)
self.pool34 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.stage4 = RSU4(64, 16, 64)
self.pool45 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.stage5 = RSU4F(64, 16, 64)
self.pool56 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
self.stage6 = RSU4F(64, 16, 64)
# decoder
self.stage5d = RSU4F(128, 16, 64)
self.stage4d = RSU4(128, 16, 64)
self.stage3d = RSU5(128, 16, 64)
self.stage2d = RSU6(128, 16, 64)
self.stage1d = RSU7(128, 16, 64)
self.side1 = nn.Conv2d(64, out_ch, 3, padding=1)
self.side2 = nn.Conv2d(64, out_ch, 3, padding=1)
self.side3 = nn.Conv2d(64, out_ch, 3, padding=1)
self.side4 = nn.Conv2d(64, out_ch, 3, padding=1)
self.side5 = nn.Conv2d(64, out_ch, 3, padding=1)
self.side6 = nn.Conv2d(64, out_ch, 3, padding=1)
self.outconv = nn.Conv2d(6 * out_ch, out_ch, 1)
def forward(self, x):
hx = x
# stage 1
hx1 = self.stage1(hx)
hx = self.pool12(hx1)
# stage 2
hx2 = self.stage2(hx)
hx = self.pool23(hx2)
# stage 3
hx3 = self.stage3(hx)
hx = self.pool34(hx3)
# stage 4
hx4 = self.stage4(hx)
hx = self.pool45(hx4)
# stage 5
hx5 = self.stage5(hx)
hx = self.pool56(hx5)
# stage 6
hx6 = self.stage6(hx)
hx6up = _upsample_like(hx6, hx5)
# decoder
hx5d = self.stage5d(torch.cat((hx6up, hx5), 1))
hx5dup = _upsample_like(hx5d, hx4)
hx4d = self.stage4d(torch.cat((hx5dup, hx4), 1))
hx4dup = _upsample_like(hx4d, hx3)
hx3d = self.stage3d(torch.cat((hx4dup, hx3), 1))
hx3dup = _upsample_like(hx3d, hx2)
hx2d = self.stage2d(torch.cat((hx3dup, hx2), 1))
hx2dup = _upsample_like(hx2d, hx1)
hx1d = self.stage1d(torch.cat((hx2dup, hx1), 1))
# side output
d1 = self.side1(hx1d)
d2 = self.side2(hx2d)
d2 = _upsample_like(d2, d1)
d3 = self.side3(hx3d)
d3 = _upsample_like(d3, d1)
d4 = self.side4(hx4d)
d4 = _upsample_like(d4, d1)
d5 = self.side5(hx5d)
d5 = _upsample_like(d5, d1)
d6 = self.side6(hx6)
d6 = _upsample_like(d6, d1)
# 6个特征图 -->1个特征图
d0 = self.outconv(torch.cat((d1, d2, d3, d4, d5, d6), 1))
return torch.sigmoid(d0), torch.sigmoid(d1), torch.sigmoid(d2), torch.sigmoid(d3), torch.sigmoid(
d4), torch.sigmoid(d5), torch.sigmoid(d6)
if __name__ == '__main__':
u2net = U2NET()
x = torch.randn(1, 3, 224, 224)
y = u2net(x)
print(y[0].shape, y[1].shape, y[2].shape, y[3].shape, y[4].shape, y[5].shape, y[6].shape)