rmdort

import React from 'react'
import ReactDOM from 'react-dom'

module.exports = (WrappedComponent) => {
  class FadeInComponent extends React.Component {
    componentDidMount () {
      // Get the components DOM node
      var elem = ReactDOM.findDOMNode(this)
      // Set the opacity of the element to 0
      elem.style.opacity = 0

rmdort

import React from 'react'
import emitter from './../../emitter'
import { compose, lifecycle, withStateHandlers } from 'recompose'

/* Flag to check if events have been attached */
var attached = false

export default function withKeydown (options) {
  return (WrappedComponent) => {
    return compose(

rmdort

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':

rmdort

class AttentionLSTM(LSTM):
    """LSTM with attention mechanism

    This is an LSTM incorporating an attention mechanism into its hidden states.
    Currently, the context vector calculated from the attended vector is fed
    into the model's internal states, closely following the model by Xu et al.
    (2016, Sec. 3.1.2), using a soft attention model following
    Bahdanau et al. (2014).

    The layer expects two inputs instead of the usual one:

rmdort

{ test: require.resolve("react"), loader: "expose-loader?React" },
{ test: require.resolve("react-dom"), loader: "expose-loader?ReactDOM" },
{
  test: /redux\/es\/index.js/,
  use: [
    {
      loader: 'expose-loader',
      options: 'Redux'
    }
  ]

rmdort

class AttentionWithContext(Layer):
    """
        Attention operation, with a context/query vector, for temporal data.
        Supports Masking.
        Follows the work of Yang et al. [https://www.cs.cmu.edu/~diyiy/docs/naacl16.pdf]
        "Hierarchical Attention Networks for Document Classification"
        by using a context vector to assist the attention
        # Input shape
            3D tensor with shape: `(samples, steps, features)`.
        # Output shape

rmdort

class AttentionLayer(Layer):
    '''
    Attention layer. 
    Usage:
        lstm_layer = LSTM(dim, return_sequences=True)
        attention = AttentionLayer()(lstm_layer)
        sentenceEmb = merge([lstm_layer, attention], mode=lambda x:x[1]*x[0], output_shape=lambda x:x[0])
        sentenceEmb = Lambda(lambda x:K.sum(x, axis=1), output_shape=lambda x:(x[0],x[2]))(sentenceEmb)
    '''
    def __init__(self, init='glorot_uniform', kernel_regularizer=None, bias_regularizer=None, kernel_constraint=None, bias_constraint=None,  **kwargs):

rmdort

from keras import backend as K
from keras.layers import Input, Dense, merge, Dropout, Lambda, LSTM, Masking
from keras.models import Model, Sequential
from keras.optimizers import SGD, RMSprop, Adam, Nadam
from sys import argv
import argparse
import csv
import json
import numpy as np
import pickle

rmdort

from keras.layers.core import Layer  
from keras import initializers, regularizers, constraints  
from keras import backend as K

class Attention(Layer):
    def __init__(self,
                 kernel_regularizer=None, bias_regularizer=None,
                 kernel_constraint=None, bias_constraint=None,
                 use_bias=True, **kwargs):
        """

rmdort

from __future__ import print_function

import json
import os
import numpy as np

from gensim.models import Word2Vec
from gensim.utils import simple_preprocess
from keras.engine import Input
from keras.layers import Embedding, merge