phreeza

import tensorflow as tf

node1 = tf.constant(3.0, tf.float32)
node2 = tf.constant(4.0) # also tf.float32 implicitly

with tf.Session() as sess:
    W = tf.Variable([.3], tf.float32, name='W')
    b = tf.Variable([-.3], tf.float32, name='b')
    x = tf.placeholder(tf.float32, name='x')
    with tf.name_scope("LinearModel"):

phreeza

{
  "embeddings": [
    {
      "tensorName": "Arxiv Titles",
      "tensorShape": [
        10000,
        256
      ],
      "tensorPath": "https://gist.githubusercontent.com/phreeza/e6a8f136fcda76bb7820f788e87e8681/raw/967badf2f7794a32e862c4ee2a8a65b59b118fb8/embeddings.tsv",
      "metadataPath": "https://gist.github.com/phreeza/e6a8f136fcda76bb7820f788e87e8681/raw/967badf2f7794a32e862c4ee2a8a65b59b118fb8/metadata.tsv"

phreeza

0.871428	0.818533	0.616601	-0.896398	0.750342	-0.0670242	-0.985361	-0.901136	-0.799989	0.661025	0.896552	-0.999996	-0.815607	-0.999946	0.210674	-0.795743	-0.936592	0.984476	0.415128	-0.640509	0.934588	0.483844	0.399479	0.215688	-0.992214	0.324514	0.454484	-0.800055	-0.999993	0.788731	-0.28611	-0.0720174	0.0251022	0.588688	0.598253	0.857084	0.999794	-0.953029	-0.865772	-0.289119	0.999546	-0.709774	-0.415915	0.0922971	-0.997911	-0.108204	-0.999999	-0.414267	-0.799834	-0.0698598	0.572549	0.410644	-0.790586	0.293573	0.999865	-0.476083	-0.678337	-0.662886	-0.999999	-0.136961	0.70228	0.05713	-0.96455	-0.715666	0.996947	-0.777469	0.999629	0.887067	0.506511	-0.691616	0.676756	-0.918784	0.835962	0.451829	-0.801001	0.0379395	0.999999	-0.096177	-1.0	0.977844	-0.771265	0.999997	0.97939	0.19234	-0.641295	-0.0612696	0.916226	0.447681	-0.651528	-0.844617	-0.661612	0.413032	0.989486	-0.897041	-0.685231	-0.335238	0.302788	-0.710447	-0.42624	0.914872	-0.312054	0.156264	0.983085	0.925359	0.916282	0.283454	0.371099	0.0488607	0.3

phreeza

import glob

entries = []
for n,fname in enumerate(glob.glob('/Users/tom/Downloads/data/*/*.txt')):
    f = open(fname)
    s = f.readlines()
    x = [g.split('\t') for g in ' '.join(s).strip().split('\n ----------\n')][:-1]
    if n%1000 == 0:
        print n,fname
    for raw_entry in x:

phreeza

# adapted from http://stackoverflow.com/a/12502560/379300
# Output should be valid markdown, so it can be turned into a nice pdf with pandoc
import poppler
import sys
import urllib
import os

def main():
    input_filename = sys.argv[1]
    # http://blog.hartwork.org/?p=612

phreeza

# This script is released 'as is' into the public domain
from math import cos,sin
import os
from time import sleep
def y(p):
    return (sin(p)**3)
def x(p):
    return -(13*cos(p)-5*cos(2*p)-2*cos(3*p)-cos(4*t))/16
while True:
    for r in range(14):

phreeza

# -*- coding: utf-8 -*-
# -*- mode: python -*-
# Adapted from mpl_toolkits.axes_grid2
# LICENSE: Python Software Foundation (http://docs.python.org/license.html)

from matplotlib.offsetbox import AnchoredOffsetbox
class AnchoredScaleBar(AnchoredOffsetbox):
    def __init__(self, transform, sizex=0, sizey=0, labelx=None, labely=None, loc=4,
                 pad=0.1, borderpad=0.1, sep=2, prop=None, **kwargs):
        """

phreeza

Keybase proof

I hereby claim:

• I am phreeza on github.
• I am tmco (https://keybase.io/tmco) on keybase.
• I have a public key whose fingerprint is CD4C 0BFB 64C8 D681 4227 561E 5924 70A9 0C46 A0EE

To claim this, I am signing this object:

phreeza

import urllib
import datetime as dt
from datetime import timedelta
import pytz
from PIL import Image
import numpy as np
import subprocess
import socket
import os

phreeza

# Test the regularisation parameter on the convolutional Layer

from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.convolutional import Convolution2D
from keras.layers.core import Dense,Flatten
from keras.utils import np_utils
from keras.regularizers import l2

import numpy as np