|
|
""" |
|
|
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 |
|
|
from torch import nn |
|
|
|
|
|
''' |
|
|
Source - https://github.com/4uiiurz1/pytorch-nested-unet |
|
|
An implementation of this paper - https://arxiv.org/abs/1807.10165 |
|
|
''' |
|
|
|
|
|
|
|
|
class VGGBlock(nn.Module): |
|
|
def __init__(self, in_channels, middle_channels, out_channels): |
|
|
super().__init__() |
|
|
self.relu = nn.ReLU(inplace=True) |
|
|
self.conv1 = nn.Conv2d(in_channels, middle_channels, 3, padding=1) |
|
|
self.bn1 = nn.BatchNorm2d(middle_channels) |
|
|
self.conv2 = nn.Conv2d(middle_channels, out_channels, 3, padding=1) |
|
|
self.bn2 = nn.BatchNorm2d(out_channels) |
|
|
|
|
|
def forward(self, x): |
|
|
out = self.conv1(x) |
|
|
out = self.bn1(out) |
|
|
out = self.relu(out) |
|
|
|
|
|
out = self.conv2(out) |
|
|
out = self.bn2(out) |
|
|
out = self.relu(out) |
|
|
|
|
|
return out |
|
|
|
|
|
class NestedUNet(nn.Module): |
|
|
def __init__(self, input_channels=1, out_channels=512): |
|
|
super().__init__() |
|
|
|
|
|
nb_filter = [32, 64, 128, 256, 512] |
|
|
|
|
|
self.pool = nn.MaxPool2d(2, 2) |
|
|
self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True) |
|
|
|
|
|
self.conv0_0 = VGGBlock(input_channels, nb_filter[0], nb_filter[0]) |
|
|
self.conv1_0 = VGGBlock(nb_filter[0], nb_filter[1], nb_filter[1]) |
|
|
self.conv2_0 = VGGBlock(nb_filter[1], nb_filter[2], nb_filter[2]) |
|
|
self.conv3_0 = VGGBlock(nb_filter[2], nb_filter[3], nb_filter[3]) |
|
|
self.conv4_0 = VGGBlock(nb_filter[3], nb_filter[4], nb_filter[4]) |
|
|
|
|
|
self.conv0_1 = VGGBlock(nb_filter[0]+nb_filter[1], nb_filter[0], nb_filter[0]) |
|
|
self.conv1_1 = VGGBlock(nb_filter[1]+nb_filter[2], nb_filter[1], nb_filter[1]) |
|
|
self.conv2_1 = VGGBlock(nb_filter[2]+nb_filter[3], nb_filter[2], nb_filter[2]) |
|
|
self.conv3_1 = VGGBlock(nb_filter[3]+nb_filter[4], nb_filter[3], nb_filter[3]) |
|
|
|
|
|
self.conv0_2 = VGGBlock(nb_filter[0]*2+nb_filter[1], nb_filter[0], nb_filter[0]) |
|
|
self.conv1_2 = VGGBlock(nb_filter[1]*2+nb_filter[2], nb_filter[1], nb_filter[1]) |
|
|
self.conv2_2 = VGGBlock(nb_filter[2]*2+nb_filter[3], nb_filter[2], nb_filter[2]) |
|
|
|
|
|
self.conv0_3 = VGGBlock(nb_filter[0]*3+nb_filter[1], nb_filter[0], nb_filter[0]) |
|
|
self.conv1_3 = VGGBlock(nb_filter[1]*3+nb_filter[2], nb_filter[1], nb_filter[1]) |
|
|
|
|
|
self.conv0_4 = VGGBlock(nb_filter[0]*4+nb_filter[1], nb_filter[0], nb_filter[0]) |
|
|
|
|
|
self.final = nn.Conv2d(nb_filter[0], out_channels, kernel_size=1) |
|
|
|
|
|
|
|
|
def forward(self, input): |
|
|
x0_0 = self.conv0_0(input) |
|
|
x1_0 = self.conv1_0(self.pool(x0_0)) |
|
|
x0_1 = self.conv0_1(torch.cat([x0_0, self.up(x1_0)], 1)) |
|
|
|
|
|
x2_0 = self.conv2_0(self.pool(x1_0)) |
|
|
x1_1 = self.conv1_1(torch.cat([x1_0, self.up(x2_0)], 1)) |
|
|
x0_2 = self.conv0_2(torch.cat([x0_0, x0_1, self.up(x1_1)], 1)) |
|
|
|
|
|
x3_0 = self.conv3_0(self.pool(x2_0)) |
|
|
x2_1 = self.conv2_1(torch.cat([x2_0, self.up(x3_0)], 1)) |
|
|
x1_2 = self.conv1_2(torch.cat([x1_0, x1_1, self.up(x2_1)], 1)) |
|
|
x0_3 = self.conv0_3(torch.cat([x0_0, x0_1, x0_2, self.up(x1_2)], 1)) |
|
|
|
|
|
x4_0 = self.conv4_0(self.pool(x3_0)) |
|
|
x3_1 = self.conv3_1(torch.cat([x3_0, self.up(x4_0)], 1)) |
|
|
x2_2 = self.conv2_2(torch.cat([x2_0, x2_1, self.up(x3_1)], 1)) |
|
|
x1_3 = self.conv1_3(torch.cat([x1_0, x1_1, x1_2, self.up(x2_2)], 1)) |
|
|
x0_4 = self.conv0_4(torch.cat([x0_0, x0_1, x0_2, x0_3, self.up(x1_3)], 1)) |
|
|
|
|
|
output = self.final(x0_4) |
|
|
return output |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
