chore: import upstream snapshot with attribution

textdiffuser/model/text_segmenter/unet.py

@@ -0,0 +1,53 @@
+# ------------------------------------------
+# TextDiffuser: Diffusion Models as Text Painters
+# Paper Link: https://arxiv.org/abs/2305.10855
+# Code Link: https://github.com/microsoft/unilm/tree/master/textdiffuser
+# Copyright (c) Microsoft Corporation.
+# This file define the architecture of unet.
+# ------------------------------------------
+
+import torch.nn.functional as F
+from model.text_segmenter.unet_parts import *
+
+
+class UNet(nn.Module):
+    def __init__(self, n_channels, n_classes, bilinear=True):
+        super(UNet, self).__init__()
+        self.n_channels = n_channels
+        self.n_classes = n_classes
+        self.bilinear = bilinear
+
+        self.inc = DoubleConv(n_channels, 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)
+        # logits = torch.sigmoid(logits)
+        return logits
+
+if __name__ == '__main__':
+    net = UNet(39,39,True)
+
+    net = net.cuda()
+
+    image = torch.Tensor(32,39,64,64).cuda()
+    result = net(image)
+    print(result.shape)

textdiffuser/model/text_segmenter/unet_parts.py

@@ -0,0 +1,82 @@
+# ------------------------------------------
+# TextDiffuser: Diffusion Models as Text Painters
+# Paper Link: https://arxiv.org/abs/2305.10855
+# Code Link: https://github.com/microsoft/unilm/tree/master/textdiffuser
+# Copyright (c) Microsoft Corporation.
+# This file define the architecture of unet.
+# ------------------------------------------
+
+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),
+            nn.BatchNorm2d(mid_channels),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(mid_channels, out_channels, kernel_size=3, padding=1),
+            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 CHW
+        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])
+
+        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)