| # from https://github.com/milesial/Pytorch-UNet/tree/master | |
| # This is a UNet model for CARRADA and KuRALS | |
| import torch | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| class DoubleConv(nn.Module): | |
| """(convolution => [BN] => ReLU) * 2""" | |
| def __init__(self, in_channels, out_channels, mid_channels=None): | |
| super().__init__() | |
| if not mid_channels: | |
| mid_channels = out_channels | |
| self.double_conv = nn.Sequential( | |
| nn.Conv2d(in_channels, mid_channels, kernel_size=3, padding=1, bias=False), | |
| nn.BatchNorm2d(mid_channels), | |
| nn.ReLU(inplace=True), | |
| nn.Conv2d(mid_channels, out_channels, kernel_size=3, padding=1, bias=False), | |
| nn.BatchNorm2d(out_channels), | |
| nn.ReLU(inplace=True) | |
| ) | |
| def forward(self, x): | |
| return self.double_conv(x) | |
| class Down(nn.Module): | |
| """Downscaling with maxpool then double conv""" | |
| def __init__(self, in_channels, out_channels): | |
| super().__init__() | |
| self.maxpool_conv = nn.Sequential( | |
| nn.MaxPool2d(2), | |
| DoubleConv(in_channels, out_channels) | |
| ) | |
| def forward(self, x): | |
| return self.maxpool_conv(x) | |
| class Up(nn.Module): | |
| """Upscaling then double conv""" | |
| def __init__(self, in_channels, out_channels, bilinear=True): | |
| super().__init__() | |
| # if bilinear, use the normal convolutions to reduce the number of channels | |
| if bilinear: | |
| self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True) | |
| self.conv = DoubleConv(in_channels, out_channels, in_channels // 2) | |
| else: | |
| self.up = nn.ConvTranspose2d(in_channels, in_channels // 2, kernel_size=2, stride=2) | |
| self.conv = DoubleConv(in_channels, out_channels) | |
| def forward(self, x1, x2): | |
| x1 = self.up(x1) | |
| # input is BCHW | |
| diffY = x2.size()[2] - x1.size()[2] | |
| diffX = x2.size()[3] - x1.size()[3] | |
| x1 = F.pad(x1, [diffX // 2, diffX - diffX // 2, | |
| diffY // 2, diffY - diffY // 2]) | |
| # if you have padding issues, see | |
| # https://github.com/HaiyongJiang/U-Net-Pytorch-Unstructured-Buggy/commit/0e854509c2cea854e247a9c615f175f76fbb2e3a | |
| # https://github.com/xiaopeng-liao/Pytorch-UNet/commit/8ebac70e633bac59fc22bb5195e513d5832fb3bd | |
| x = torch.cat([x2, x1], dim=1) | |
| return self.conv(x) | |
| class OutConv(nn.Module): | |
| def __init__(self, in_channels, out_channels): | |
| super(OutConv, self).__init__() | |
| self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1) | |
| def forward(self, x): | |
| return self.conv(x) | |
| class UNet(nn.Module): | |
| def __init__(self, n_classes, n_frames=5, bilinear=True): | |
| """ | |
| Args: | |
| n_classes : _description_ | |
| n_frames : _description_. Defaults to 5. | |
| bilinear : Bilinear interpolation or ConvTranspose2d. | |
| """ | |
| super(UNet, self).__init__() | |
| self.n_channels = n_frames | |
| self.n_classes = n_classes | |
| self.bilinear = bilinear | |
| # lt@20240406 reduce resolution | |
| # self.pool0 = nn.MaxPool2d(2, stride=2, ceil_mode=True) | |
| self.inc = (DoubleConv(n_frames, 64)) | |
| self.down1 = (Down(64, 128)) | |
| self.down2 = (Down(128, 256)) | |
| self.down3 = (Down(256, 512)) | |
| factor = 2 if bilinear else 1 | |
| self.down4 = (Down(512, 1024 // factor)) | |
| self.up1 = (Up(1024, 512 // factor, bilinear)) | |
| self.up2 = (Up(512, 256 // factor, bilinear)) | |
| self.up3 = (Up(256, 128 // factor, bilinear)) | |
| self.up4 = (Up(128, 64, bilinear)) | |
| self.outc = (OutConv(64, n_classes)) | |
| def forward(self, x): | |
| # lt@20240406 reduce resolution | |
| # x = self.pool0(x) | |
| # lt@20240408 add resolution | |
| # x = F.interpolate(x, scale_factor=2, mode='bilinear', align_corners=True) | |
| x1 = self.inc(x) | |
| x2 = self.down1(x1) | |
| x3 = self.down2(x2) | |
| x4 = self.down3(x3) | |
| x5 = self.down4(x4) | |
| x = self.up1(x5, x4) | |
| x = self.up2(x, x3) | |
| x = self.up3(x, x2) | |
| x = self.up4(x, x1) | |
| logits = self.outc(x) | |
| # lt@20240406 recover resolution | |
| # logits = F.interpolate(logits, scale_factor=2, mode='bilinear', align_corners=True) | |
| # lt@20240408 add resolution | |
| # logits = F.interpolate(logits, scale_factor=0.5, mode='bilinear', align_corners=True) | |
| return logits | |
| # from https://github.com/milesial/Pytorch-UNet/tree/master | |
| # import torch | |
| # import torch.nn as nn | |
| # import torch.nn.functional as F | |
| # lt@20240315 spatial group normalization | |
| # lt@20240316 change fixed value 200 to w//4. | |
| # class DoubleConv(nn.Module): | |
| # """(convolution => [SGN] => ReLU) * 2""" | |
| # def __init__(self, in_channels, out_channels, mid_channels=None): | |
| # super().__init__() | |
| # if not mid_channels: | |
| # mid_channels = out_channels | |
| # self.conv1 = nn.Conv2d(in_channels, mid_channels, kernel_size=3, padding=1, bias=False) | |
| # self.bn1_1 = nn.BatchNorm2d(mid_channels) | |
| # self.bn1_2 = nn.BatchNorm2d(mid_channels) | |
| # self.relu = nn.ReLU(inplace=True) | |
| # self.conv2 = nn.Conv2d(mid_channels, out_channels, kernel_size=3, padding=1, bias=False) | |
| # self.bn2_1 = nn.BatchNorm2d(out_channels) | |
| # self.bn2_2 = nn.BatchNorm2d(out_channels) | |
| # def forward(self, x): | |
| # b, c, h, w = x.shape | |
| # x = self.conv1(x) | |
| # x11 = self.bn1_1(x[:, :, :, :(w//4)]) | |
| # x12 = self.bn1_2(x[:, :, :, (w//4):]) | |
| # x1 = self.relu(torch.concat([x11, x12], dim=-1)) | |
| # x2 = self.conv2(x1) | |
| # x21 = self.bn2_1(x2[:, :, :, :(w//4)]) | |
| # x22 = self.bn2_2(x2[:, :, :, (w//4):]) | |
| # x2 = self.relu(torch.concat([x21, x22], dim=-1)) | |
| # return x2 | |
| # lt@20240315 Group Normalization | |
| # class DoubleConv(nn.Module): | |
| # """(convolution => [GN] => ReLU) * 2""" | |
| # def __init__(self, in_channels, out_channels, mid_channels=None): | |
| # super().__init__() | |
| # if not mid_channels: | |
| # mid_channels = out_channels | |
| # self.double_conv = nn.Sequential( | |
| # nn.Conv2d(in_channels, mid_channels, kernel_size=3, padding=1, bias=False), | |
| # nn.GroupNorm(mid_channels//16, mid_channels), | |
| # nn.ReLU(inplace=True), | |
| # nn.Conv2d(mid_channels, out_channels, kernel_size=3, padding=1, bias=False), | |
| # nn.GroupNorm(out_channels//16, out_channels), | |
| # nn.ReLU(inplace=True) | |
| # ) | |
| # def forward(self, x): | |
| # return self.double_conv(x) | |
| # class Down(nn.Module): | |
| # """Downscaling with maxpool then double conv""" | |
| # def __init__(self, in_channels, out_channels): | |
| # super().__init__() | |
| # self.maxpool_conv = nn.Sequential( | |
| # nn.MaxPool2d(2), | |
| # DoubleConv(in_channels, out_channels) | |
| # ) | |
| # def forward(self, x): | |
| # return self.maxpool_conv(x) | |
| # class Up(nn.Module): | |
| # """Upscaling then double conv""" | |
| # def __init__(self, in_channels, out_channels, bilinear=True): | |
| # super().__init__() | |
| # # if bilinear, use the normal convolutions to reduce the number of channels | |
| # if bilinear: | |
| # self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True) | |
| # self.conv = DoubleConv(in_channels, out_channels, in_channels // 2) | |
| # else: | |
| # self.up = nn.ConvTranspose2d(in_channels, in_channels // 2, kernel_size=2, stride=2) | |
| # self.conv = DoubleConv(in_channels, out_channels) | |
| # def forward(self, x1, x2): | |
| # x1 = self.up(x1) | |
| # # input is BCHW | |
| # diffY = x2.size()[2] - x1.size()[2] | |
| # diffX = x2.size()[3] - x1.size()[3] | |
| # x1 = F.pad(x1, [diffX // 2, diffX - diffX // 2, | |
| # diffY // 2, diffY - diffY // 2]) | |
| # # if you have padding issues, see | |
| # # https://github.com/HaiyongJiang/U-Net-Pytorch-Unstructured-Buggy/commit/0e854509c2cea854e247a9c615f175f76fbb2e3a | |
| # # https://github.com/xiaopeng-liao/Pytorch-UNet/commit/8ebac70e633bac59fc22bb5195e513d5832fb3bd | |
| # x = torch.cat([x2, x1], dim=1) | |
| # return self.conv(x) | |
| # class OutConv(nn.Module): | |
| # def __init__(self, in_channels, out_channels): | |
| # super(OutConv, self).__init__() | |
| # self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1) | |
| # def forward(self, x): | |
| # return self.conv(x) | |
| # class UNet(nn.Module): | |
| # def __init__(self, n_classes, n_frames=5, bilinear=True): | |
| # """ | |
| # Args: | |
| # n_classes : _description_ | |
| # n_frames : _description_. Defaults to 5. | |
| # bilinear : Bilinear interpolation or ConvTranspose2d. | |
| # """ | |
| # super(UNet, self).__init__() | |
| # self.n_channels = n_frames | |
| # self.n_classes = n_classes | |
| # self.bilinear = bilinear | |
| # self.inc = (DoubleConv(n_frames, 64)) | |
| # self.down1 = (Down(64, 128)) | |
| # self.down2 = (Down(128, 256)) | |
| # self.down3 = (Down(256, 512)) | |
| # factor = 2 if bilinear else 1 | |
| # self.down4 = (Down(512, 1024 // factor)) | |
| # self.up1 = (Up(1024, 512 // factor, bilinear)) | |
| # self.up2 = (Up(512, 256 // factor, bilinear)) | |
| # self.up3 = (Up(256, 128 // factor, bilinear)) | |
| # self.up4 = (Up(128, 64, bilinear)) | |
| # self.outc = (OutConv(64, n_classes)) | |
| # def forward(self, x): | |
| # x1 = self.inc(x) | |
| # x2 = self.down1(x1) | |
| # x3 = self.down2(x2) | |
| # x4 = self.down3(x3) | |
| # x5 = self.down4(x4) | |
| # x = self.up1(x5, x4) | |
| # x = self.up2(x, x3) | |
| # x = self.up3(x, x2) | |
| # x = self.up4(x, x1) | |
| # logits = self.outc(x) | |
| # return logits |