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

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

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

    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

import torch
import numpy as np

class Tester:

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

ShairozS

class LabeledContrastiveDataset(Dataset):
    """
    Take a folder containing sub-folders of images, where the sub-folder name is the image class, and generate
    pairs of images with the same class label for contrastive learning. This procedure fixes the batch size since
    every batch contains all classes and every batch element is a unique pairing of each class. 
    """

    def __init__(self, folder, transforms=None):
        
        labels = os.listdir(folder)

ShairozS

import torch
import numpy as np

class Trainer:

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

ShairozS

import torch
import numpy as np



class Trainer:

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

ShairozS

class ContrastiveLoss(torch.nn.Module):
    
    
    """
    Contrastive loss function.
    Based on: http://yann.lecun.com/exdb/publis/pdf/hadsell-chopra-lecun-06.pdf
    
    args:
        distance (function): A function that returns the distance between two tensors - should be a valid metric over R; default= L2 distance
        margin (scalar): The margin value between positive and negative class ; default=1.0

ShairozS