paduvi

import torch
import torch.nn as nn
import torch.nn.init as init

dropout_prob = 0.5


class FlatCnnLayer(nn.Module):
    def __init__(self, embedding_size, sequence_length, filter_sizes=[3, 4, 5], out_channels=128):
        super(FlatCnnLayer, self).__init__()

lmclupr

bkj

#!/usr/bin/env python

"""
    pytorch_lifted_loss.py
"""

import torch
import torch.nn as nn
from torch.autograd import Variable

chrischoy

import tensorflow as tf
import numpy as np

def smoothed_metric_loss(input_tensor, name='smoothed_triplet_loss', margin=1):
    '''
    input_tensor: require a tensor with predefined dimensions (No None dimension)
                  Every two consecutive vectors must be a positive pair. There
                  should not be more than one pair from each class.
    '''
    with tf.variable_scope(name):

cbaziotis

def dot_product(x, kernel):
    """
    Wrapper for dot product operation, in order to be compatible with both
    Theano and Tensorflow
    Args:
        x (): input
        kernel (): weights
    Returns:
    """
    if K.backend() == 'tensorflow':

lawliet89

// http://en.literateprograms.org/Merge_sort_(C_Plus_Plus)
#include <algorithm>
#include <iterator>
#include <iostream>

// Note: InputIterator must allow the minus operator -- i.e. RandomAccess
// The end element is AFTER the last element
// output refers to the iterator for the first output item
// You can mix and match different input and output iterators (i.e. vectors, arrays etc.)
template <typename InputIterator, typename OutputIterator> void mergesort(InputIterator start, InputIterator end, OutputIterator output){

bwhite

"""Information Retrieval metrics

Useful Resources:
http://www.cs.utexas.edu/~mooney/ir-course/slides/Evaluation.ppt
http://www.nii.ac.jp/TechReports/05-014E.pdf
http://www.stanford.edu/class/cs276/handouts/EvaluationNew-handout-6-per.pdf
http://hal.archives-ouvertes.fr/docs/00/72/67/60/PDF/07-busa-fekete.pdf
Learning to Rank for Information Retrieval (Tie-Yan Liu)
"""
import numpy as np