ozancaglayan

Keybase proof

I hereby claim:

• I am ozancaglayan on github.
• I am ozancaglayan (https://keybase.io/ozancaglayan) on keybase.
• I have a public key whose fingerprint is 2C3B 4DA8 7E9B B14C 2B6B CB51 E96D AF7F F229 6D8C

To claim this, I am signing this object:

ozancaglayan

--- c384-ce12288-pe1536-h256-bs256-lr0.03.log	2015-10-29 22:28:40.539747323 +0100
+++ c384-ce12288-pe1536-h256-bs256-lr0.03-repeatbug.log	2015-11-13 15:41:20.820063590 +0100
@@ -12,6 +12,7 @@
     6: Tesla K40c with 15 CPUs x 192 threads running at 0.74 Ghz, 11519 MBytes of memory, use -arch=sm_35, utilization 0%
     7: Tesla K40c with 15 CPUs x 192 threads running at 0.74 Ghz, 11519 MBytes of memory, use -arch=sm_35, utilization 0%
  - using 8 devices in parallel: 0 1 2 3 4 5 6 7
+ - repeating these 1 machine(s) 32 times
 #### GPU allocate local data for 8 GPU
 #### GPU 0: use local data_in from MachSplit
 #### GPU 1: allocate local data_in=0x2162a0000

ozancaglayan

Creating a new machine
 - initializing projections with random values in the range 0.1
 - initializing weights with random values in the range 0.1
Initializing Nvidia GPU card
 - found 8 cards:
    0: Tesla K40c with 15 CPUs x 192 threads running at 0.74 Ghz, 11519 MBytes of memory, use -arch=sm_35, utilization 0%
    1: Tesla K40c with 15 CPUs x 192 threads running at 0.74 Ghz, 11519 MBytes of memory, use -arch=sm_35, utilization 0%
    2: Tesla K40c with 15 CPUs x 192 threads running at 0.74 Ghz, 11519 MBytes of memory, use -arch=sm_35, utilization 0%
    3: Tesla K40c with 15 CPUs x 192 threads running at 0.74 Ghz, 11519 MBytes of memory, use -arch=sm_35, utilization 0%
    4: Tesla K40c with 15 CPUs x 192 threads running at 0.74 Ghz, 11519 MBytes of memory, use -arch=sm_35, utilization 0%

ozancaglayan

#!/usr/bin/env python

from keras.layers.core import Dense
from keras.models import Sequential
from keras.optimizers import RMSprop, Adadelta, Adagrad, Adam, SGD
from keras.callbacks import Callback

import numpy as np

class Test(Callback):

ozancaglayan

# pp: (batch, sequence_step, target vocabulary probabilities)
# yy: (batch, sequence_step's true label)

# Soru: pp[yy] gibi dogru yerlerden dogru olasiliklari nasi cekebilirim?

In [211]: pp.shape
Out[211]: (256, 33, 20004)

In [212]: yy.shape
Out[212]: (256, 33)

ozancaglayan

#!/usr/bin/env python

import sys

import numpy as np
import time

import theano
import theano.tensor as T

ozancaglayan

#!/usr/bin/env python
import sys
import time

def model():
    print "model"
    try:
        while 1:
            print "loop"
            time.sleep(2)

ozancaglayan

losses = [57.4, 50.7, 40.9, 39.6 ,37.9, 37.5, 36.3, 35.7, 36.5, 35.13, 36.33, 34.37, 34.78, 34.67, 34.44, 35.2, 35.66, 32.47, 34.6, 34.7, 35.14, 34.5]

import numpy as np
vhist = []
patience = 10
bad_c = 0
use_bleu = False

for i in range(len(losses)):
  loss = losses[i]

ozancaglayan

local argparse = require "argparse"
local moses = require "moses"

local parser = argparse("build_dictionary", "example")

parser:argument("input", "Input text file"):args('+')
parser:option('-o --output', 'Output directory', '.')
parser:option('-m --minfreq', 'Filter out words occuring < m times.', 0)

local args = parser:parse()

ozancaglayan

       Wemb_enc, -0.05387, 0.05577
       Wemb_dec, -0.05280, 0.05521
      encoder_W, -0.05016, 0.04749
      encoder_b, 0.00000, 0.00000
      encoder_U, -0.17179, 0.16453
     encoder_Wx, -0.04784, 0.04707
     encoder_bx, 0.00000, 0.00000
     encoder_Ux, -0.15236, 0.15887
    encoder_r_W, -0.04918, 0.04668
    encoder_r_b, 0.00000, 0.00000