code/recognization/resnet.py

"""
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)