""" Paper: "UTRNet: High-Resolution Urdu Text Recognition In Printed Documents" presented at ICDAR 2023 Authors: Abdur Rahman, Arjun Ghosh, Chetan Arora GitHub Repository: https://github.com/abdur75648/UTRNet-High-Resolution-Urdu-Text-Recognition Project Website: https://abdur75648.github.io/UTRNet/ Copyright (c) 2023-present: This work is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/) """ import torch.nn as nn # Code For ResNet Feature Extractor class BasicBlock(nn.Module): expansion = 1 def __init__(self, inplanes, planes, stride=1, downsample=None): super(BasicBlock, self).__init__() self.conv1 = self._conv3x3(inplanes, planes) self.bn1 = nn.BatchNorm2d(planes) self.conv2 = self._conv3x3(planes, planes) self.bn2 = nn.BatchNorm2d(planes) self.relu = nn.ReLU(inplace=True) self.downsample = downsample self.stride = stride def _conv3x3(self, in_planes, out_planes, stride=1): "3x3 convolution with padding" return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False) def forward(self, x): residual = x out = self.conv1(x) out = self.bn1(out) out = self.relu(out) out = self.conv2(out) out = self.bn2(out) if self.downsample is not None: residual = self.downsample(x) out += residual out = self.relu(out) return out class ResNet_model(nn.Module): def __init__(self, input_channel, output_channel, block, layers): super(ResNet_model, self).__init__() self.output_channel_block = [int(output_channel / 4), int(output_channel / 2), output_channel, output_channel] self.inplanes = int(output_channel / 8) self.conv0_1 = nn.Conv2d(input_channel, int(output_channel / 16), kernel_size=3, stride=1, padding=1, bias=False) self.bn0_1 = nn.BatchNorm2d(int(output_channel / 16)) self.conv0_2 = nn.Conv2d(int(output_channel / 16), self.inplanes, kernel_size=3, stride=1, padding=1, bias=False) self.bn0_2 = nn.BatchNorm2d(self.inplanes) self.relu = nn.ReLU(inplace=True) self.maxpool1 = nn.MaxPool2d(kernel_size=2, stride=2, padding=0) self.layer1 = self._make_layer(block, self.output_channel_block[0], layers[0]) self.conv1 = nn.Conv2d(self.output_channel_block[0], self.output_channel_block[ 0], kernel_size=3, stride=1, padding=1, bias=False) self.bn1 = nn.BatchNorm2d(self.output_channel_block[0]) self.maxpool2 = nn.MaxPool2d(kernel_size=2, stride=2, padding=0) self.layer2 = self._make_layer(block, self.output_channel_block[1], layers[1], stride=1) self.conv2 = nn.Conv2d(self.output_channel_block[1], self.output_channel_block[ 1], kernel_size=3, stride=1, padding=1, bias=False) self.bn2 = nn.BatchNorm2d(self.output_channel_block[1]) self.maxpool3 = nn.MaxPool2d(kernel_size=2, stride=(2, 1), padding=(0, 1)) self.layer3 = self._make_layer(block, self.output_channel_block[2], layers[2], stride=1) self.conv3 = nn.Conv2d(self.output_channel_block[2], self.output_channel_block[ 2], kernel_size=3, stride=1, padding=1, bias=False) self.bn3 = nn.BatchNorm2d(self.output_channel_block[2]) self.layer4 = self._make_layer(block, self.output_channel_block[3], layers[3], stride=1) self.conv4_1 = nn.Conv2d(self.output_channel_block[3], self.output_channel_block[ 3], kernel_size=2, stride=(2, 1), padding=(0, 1), bias=False) self.bn4_1 = nn.BatchNorm2d(self.output_channel_block[3]) self.conv4_2 = nn.Conv2d(self.output_channel_block[3], self.output_channel_block[ 3], kernel_size=2, stride=1, padding=0, bias=False) self.bn4_2 = nn.BatchNorm2d(self.output_channel_block[3]) def _make_layer(self, block, planes, blocks, stride=1): downsample = None if stride != 1 or self.inplanes != planes * block.expansion: downsample = nn.Sequential( nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(planes * block.expansion), ) layers = [] layers.append(block(self.inplanes, planes, stride, downsample)) self.inplanes = planes * block.expansion for i in range(1, blocks): layers.append(block(self.inplanes, planes)) return nn.Sequential(*layers) def forward(self, x): # print ("INPUT SHAPE", x.shape) # INPUT SHAPE torch.Size([16, 1, 32, 400]) x = self.conv0_1(x) x = self.bn0_1(x) x = self.relu(x) x = self.conv0_2(x) x = self.bn0_2(x) x = self.relu(x) # ([16, 64, 32, 400]) # print ("XXXX", x.shape) x = self.maxpool1(x) # print ("After 1st Block", x.shape) # After 1st Block torch.Size([16, 64, 16, 200]) x = self.layer1(x) x = self.conv1(x) x = self.bn1(x) x = self.relu(x) x = self.maxpool2(x) # print ("After 2nd Block", x.shape) # After 2nd Block torch.Size([16, 128, 8, 100]) x = self.layer2(x) x = self.conv2(x) x = self.bn2(x) x = self.relu(x) x = self.maxpool3(x) # print ("After 3rd Block", x.shape) # After 3rd Block torch.Size([16, 256, 4, 101]) x = self.layer3(x) x = self.conv3(x) x = self.bn3(x) x = self.relu(x) # print ("After 4th Block", x.shape) # After 4th Block torch.Size([16, 512, 4, 101]) x = self.layer4(x) x = self.conv4_1(x) x = self.bn4_1(x) x = self.relu(x) x = self.conv4_2(x) x = self.bn4_2(x) x = self.relu(x) # print ("Output Shape", x.shape) # Output Shape torch.Size([16, 512, 1, 101]) return x class ResNet(nn.Module): """ FeatureExtractor of FAN (http://openaccess.thecvf.com/content_ICCV_2017/papers/Cheng_Focusing_Attention_Towards_ICCV_2017_paper.pdf) """ def __init__(self, input_channel=1, output_channel=512): super(ResNet, self).__init__() self.ConvNet = ResNet_model(input_channel, output_channel, BasicBlock, [1, 2, 5, 3]) def forward(self, input): return self.ConvNet(input) # import torch # x = torch.randn(1, 1, 32, 400) # net = ResNet() # out = net(x) # print(out.shape)