cerisara

/**
 * Iterative reduce with
 * flat map using map partitions
 *
 * @author Adam Gibson
   modified by Christophe Cerisara
 */
 
 public class IterativeReduceFlatMap implements FlatMapFunction<Iterator<DataSet>, INDArray> {

cerisara

# X_train contains word indices (single int between 0 and max_words)
# Y_train0 contains class indices (single int between 0 and nb_classes)

X_train = sequence.pad_sequences(X_train, maxlen=maxlen, padding='post')
X_test = sequence.pad_sequences(X_test, maxlen=maxlen, padding='post')

Y_train = np.zeros((batchSize,globvars.nb_classes))#,dtype=np.float32)
for t in range(batchSize):
    Y_train[t][Y_train0[t]]=1
Y_test = np.zeros((len(Y_test0),globvars.nb_classes))#,dtype=np.float32)

cerisara

import numpy as np
import matplotlib.pyplot as plt

from keras.models import Sequential
from keras.layers.core import Dense, Activation
from keras.optimizers import SGD

from sklearn.metrics import mean_squared_error

tau=2*np.pi

cerisara

complete_sentences = [["*-START-*"] for a in range(1000)]
sents = np.zeros((nb_samples, timesteps+1, len(vocab)))

for x in range(nb_samples):
    sents[i,0,word2index["*-START-*"]] = 1. # init the sequences

for t in range(timesteps):
    preds = self.model.predict(sents[:,0:t+1], verbose=0)
    # get the maximum predictions for this timestep for each sample
    next_word_indices = np.argmax(preds[:,t], axis=1)

cerisara

import numpy as np

from keras.preprocessing import sequence
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten, TimeDistributedDense
from keras.layers.recurrent import LSTM
from keras.layers.embeddings import Embedding
from keras.utils import np_utils
from keras.preprocessing.text import Tokenizer
from keras.models import Graph

cerisara

#!/usr/bin/php -qC
<?php

/******************************************************************************
 *  
 *  @file           gitolab.php
 *  @author         Benoit Zohar
 *  @link           http://benoitzohar.fr/
 *  @last-edited    2015-01-09
 *  @description    Migrate projects from Gitolite to GitLab

cerisara

 
Data Parallelization with multi-GPU over TensorFlow
Jonathan Laserson <jonilaserson@gmail.com>
	
9 oct. (Il y a 2 jours)
	
À Keras-users Se désabonner

Here is how to take an existing model and do data parallelization across multiple GPUs.

cerisara

import sys

def getText(l):
    l=l.replace('\\citep','')
    l=l.replace('\\cite','')
    return l

with open(sys.argv[1],'rb') as f : ls = f.readlines()

empty=False

cerisara

#!/bin/bash

# arxiv paper ID
python2 getarxivid.py $1 > arxivids

mkdir papers

for i in $(cat arxivids)
do

cerisara

(Et pour voir les départements les plus accueillants, c'est ici: https://gist.github.com/cerisara/928ad03cf15c77dda8897c2cf49ef27d )