Spaces:
Running
Running
| # A simplified version of the original code - https://github.com/abdur75648/UTRNet-High-Resolution-Urdu-Text-Recognition | |
| import torch | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| # Code For UNet Feature Extractor - Source - https://github.com/milesial/Pytorch-UNet | |
| 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): | |
| super().__init__() | |
| 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) | |
| class UNet(nn.Module): | |
| def __init__(self, n_channels=1, n_classes=512): | |
| super(UNet, self).__init__() | |
| self.n_channels = n_channels | |
| self.n_classes = n_classes | |
| self.inc = DoubleConv(n_channels, 32) | |
| self.down1 = Down(32, 64) | |
| self.down2 = Down(64, 128) | |
| self.down3 = Down(128, 256) | |
| self.down4 = Down(256, 512) | |
| self.up1 = Up(512, 256) | |
| self.up2 = Up(256, 128) | |
| self.up3 = Up(128, 64) | |
| self.up4 = Up(64, 32) | |
| self.outc = OutConv(32, n_classes) | |
| def forward(self, x): | |
| # print(x.shape) # torch.Size([1, 1, 32, 400]) | |
| x1 = self.inc(x) | |
| # print(x1.shape) # torch.Size([1, 32, 32, 400]) | |
| x2 = self.down1(x1) | |
| # print(x2.shape) # torch.Size([1, 64, 16, 200]) | |
| x3 = self.down2(x2) | |
| # print(x3.shape) # torch.Size([1, 128, 8, 100]) | |
| x4 = self.down3(x3) | |
| # print(x4.shape) # torch.Size([1, 256, 4, 50]) | |
| x5 = self.down4(x4) | |
| # print(x5.shape) # torch.Size([1, 512, 2, 25]) | |
| # print("Upscaling...") | |
| x = self.up1(x5, x4) | |
| # print(x.shape) # torch.Size([1, 256, 4, 50]) | |
| x = self.up2(x, x3) | |
| # print(x.shape) # torch.Size([1, 128, 8, 100]) | |
| x = self.up3(x, x2) | |
| # print(x.shape) # torch.Size([1, 64, 16, 200]) | |
| x = self.up4(x, x1) | |
| # print(x.shape) # torch.Size([1, 32, 32, 400]) | |
| logits = self.outc(x) | |
| # print(logits.shape) # torch.Size([1, 512, 32, 400]) | |
| return logits | |
| # x = torch.randn(1, 1, 32, 400) | |
| # net = UNet() | |
| # out = net(x) | |
| # print(out.shape) |