ShairozS

import torch
import numpy as np

class Tester:

    ##########################
    #                        #
    #     Initialization     #
    #                        #
    ##########################

ShairozS

    def predict(self, x, y, threshold=1.0):
        '''
        Generate similarity scores for a batch of paired examples
        
        Args:
            x (torch.Tensor): An input image (B, C, 105, 105)
            y (torch.Tensor): The paired input image (B, C, 105, 105)
            threshold (float): The threshold for similarity - set to model margin (default = 1.0), set to None for raw distance outputs
            
        returns:

ShairozS

from torchvision import transforms
from torchvision.datasets import MNIST
import torchvision.models as models
import torch

BATCH_SIZE = 100

def stack(tensor, times=3):
  return(torch.cat([tensor]*times, dim=0))

ShairozS

class SiameseModel(nn.Module):
    
    '''
    Implementation of Koch et al (2015) "Siamese Neural Networks for One-shot Image Recognition"
    
    
    args:
        in_channels (int): The number of input channels in the input images
        distance (function): A function of two vectors that returns the scalar distance between them 
    '''

ShairozS

#################################################################
# This script takes in an input folder of scanned documents     #
# and reads these documents, seperates them into topics         #
# and outputs raw .txt files into the output folder, seperated  #
# by topic                                                      #
#################################################################

import os
from PIL import Image
import base64

ShairozS

def topic_label(ldamodel, topicnum):
    alltopics = ldamodel.show_topics(formatted=False)
    topic = alltopics[topicnum]
    topic = dict(topic[1])
    return(max(topic, key=lambda key: topic[key]))

ShairozS

def find_topic(textlist, dictionary, lda):
    '''
    https://stackoverflow.com/questions/16262016/how-to-predict-the-topic-of-a-new-query-using-a-trained-lda-model-using-gensim
    
     For each query ( document in the test file) , tokenize the 
     query, create a feature vector just like how it was done while training
     and create text_corpus
    '''
    
    text_corpus = []

ShairozS

from gensim import corpora, models, similarities
from gensim.parsing.preprocessing import remove_stopwords, preprocess_string

def preprocess(document):
    clean = remove_stopwords(document)
    clean = preprocess_string(document) 
    return(clean)
  
def run_lda(textlist, 
            num_topics=10,

ShairozS

def read_and_return(foldername, fileext='.txt'):
  '''
  Read all text files with fileext from foldername, and place them into a list of tuples as
  [(filename, text), ... , (filename, text)]
  '''
    allfiles = os.listdir(foldername)
    allfiles = [os.path.join(foldername, f) for f in allfiles if f.endswith(fileext)]
    alltext = []
    for filename in allfiles:
        with open(filename, 'r') as f:

ShairozS

'''
Read in a list of scanned images (as .png files > 50x50px) and output a set of .txt files containing the text content of these scans
'''


from functions import preprocess, image_to_text
from PIL import Image
import os
from spellchecker import SpellChecker