【发布时间】:2021-08-28 03:19:50
【问题描述】:
import torch
import torch.nn as nn
import torch.nn.functional as F
class double_conv(nn.Module):
'''(conv => BN => ReLU) * 2'''
def __init__(self, in_ch, out_ch):
super(double_conv, 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, x):
x = self.conv(x)
return x
class inconv(nn.Module):
def __init__(self, in_ch, out_ch):
super(inconv, self).__init__()
self.conv = double_conv(in_ch, out_ch)
def forward(self, x):
x = self.conv(x)
return x
class down(nn.Module):
def __init__(self, in_ch, out_ch):
super(down, self).__init__()
self.mpconv = nn.Sequential(
nn.MaxPool2d(2),
double_conv(in_ch, out_ch)
)
def forward(self, x):
x = self.mpconv(x)
return x
class up(nn.Module):
def __init__(self, in_ch, out_ch, bilinear=True):
super(up, self).__init__()
# would be a nice idea if the upsampling could be learned too,
# but my machine do not have enough memory to handle all those weights
if bilinear:
self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
else:
self.up = nn.ConvTranspose2d(in_ch//2, in_ch//2, 2, stride=2)
self.conv = double_conv(in_ch, out_ch)
def forward(self, x1, x2):
x1 = self.up(x1)
diffX = x1.size()[2] - x2.size()[2]
diffY = x1.size()[3] - x2.size()[3]
x2 = F.pad(x2, (diffX // 2, int(diffX / 2),
diffY // 2, int(diffY / 2)))
x = torch.cat([x2, x1], dim=1)
x = self.conv(x)
return x
class outconv(nn.Module):
def __init__(self, in_ch, out_ch):
super(outconv, self).__init__()
self.conv = nn.Conv2d(in_ch, out_ch, 1)
def forward(self, x):
x = self.conv(x)
return x
class UNet(nn.Module):
def __init__(self, n_channels, n_classes):
super(UNet, self).__init__()
self.inc = inconv(n_channels, 64)
self.down1 = down(64, 128)
self.down2 = down(128, 256)
self.down3 = down(256, 512)
self.down4 = down(512, 512)
self.up1 = up(1024, 256)
self.up2 = up(512, 128)
self.up3 = up(256, 64)
self.up4 = up(128, 64)
self.outc = outconv(64, n_classes)
def forward(self, x):
self.x1 = self.inc(x)
self.x2 = self.down1(self.x1)
self.x3 = self.down2(self.x2)
self.x4 = self.down3(self.x3)
self.x5 = self.down4(self.x4)
self.x6 = self.up1(self.x5, self.x4)
self.x7 = self.up2(self.x6, self.x3)
self.x8 = self.up3(self.x7, self.x2)
self.x9 = self.up4(self.x8, self.x1)
self.y = self.outc(self.x9)
return self.y
当我阅读 UNet 架构时,我发现它有 n_classes 作为输出。
class UNet(nn.Module):
def __init__(self, n_channels, n_classes):
但为什么它有n_classes 用于图像分割?
我正在尝试使用此代码进行图像去噪,但我无法弄清楚 n_classes 参数应该是什么,因为我没有任何类。
n_classes 是否表示多类分割?如果是,那么二进制 UNet 分割的输出是什么?
【问题讨论】:
标签: python pytorch image-segmentation unity3d-unet