recognization/vgg.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/)
"""

from torch import nn

class VGG(nn.Module):
    """ FeatureExtractor of CRNN (https://arxiv.org/pdf/1507.05717.pdf) """
    def __init__(self, input_channel=1, output_channel=512):
        super(VGG, self).__init__()
        self.output_channel = [int(output_channel / 8), int(output_channel / 4),
                               int(output_channel / 2), output_channel]
        self.ConvNet = nn.Sequential(
            nn.Conv2d(input_channel, self.output_channel[0], 3, 1, 1), nn.ReLU(True),
            nn.MaxPool2d(2, 2),
            nn.Conv2d(self.output_channel[0], self.output_channel[1], 3, 1, 1), nn.ReLU(True),
            nn.MaxPool2d(2, 2),
            nn.Conv2d(self.output_channel[1], self.output_channel[2], 3, 1, 1), nn.ReLU(True),
            nn.Conv2d(self.output_channel[2], self.output_channel[2], 3, 1, 1), nn.ReLU(True),
            nn.MaxPool2d((2, 1), (2, 1)),
            nn.Conv2d(self.output_channel[2], self.output_channel[3], 3, 1, 1, bias=False),
            nn.BatchNorm2d(self.output_channel[3]), nn.ReLU(True),
            nn.Conv2d(self.output_channel[3], self.output_channel[3], 3, 1, 1, bias=False),
            nn.BatchNorm2d(self.output_channel[3]), nn.ReLU(True),
            nn.MaxPool2d((2, 1), (2, 1)),
            nn.Conv2d(self.output_channel[3], self.output_channel[3], 2, 1, 0), nn.ReLU(True))

    def forward(self, input):
        return self.ConvNet(input)

# import torch    
# x = torch.randn(1, 1, 32, 400)
# net = VGG()
# out = net(x)
# print(out.shape)