aparrish

ajbrock

## Unrolled GAN
# A Brock, 2016
# This code implements the toy experiment for unrolled GANs.

# TODO: Make shared variables and reduce the memory transfer overhead

# Imports


import numpy as np

mgermain

import os
import requests
from bs4 import BeautifulSoup


class GSheet(object):
    base_sheet_url = 'https://spreadsheets.google.com/feeds/worksheets/{0}/private/full'
    list_worksheet_url = 'https://spreadsheets.google.com/feeds/list/{0}/{{}}/private/full'
    cell_worksheet_url = 'https://spreadsheets.google.com/feeds/cells/{0}/{{}}/private/full'
    HTTPheaders = {'content-type': 'application/atom+xml'}

bmcfee

tmramalho

import theano
import theano.tensor as T
import numpy as np
import cPickle
import random
import matplotlib.pyplot as plt

class RNN(object):

	def __init__(self, nin, n_hidden, nout):

windytan

#include <stdlib.h>
#include <math.h>
#include <string.h>
#include <fftw3.h>

#define FFTLEN 2048
#define SRATE  22050

// Return sinusoid power from complex DFT coefficients
double power (fftw_complex coeff) {

jboner

Latency Comparison Numbers (~2012)
----------------------------------
L1 cache reference                           0.5 ns
Branch mispredict                            5   ns
L2 cache reference                           7   ns                      14x L1 cache
Mutex lock/unlock                           25   ns
Main memory reference                      100   ns                      20x L2 cache, 200x L1 cache
Compress 1K bytes with Zippy             3,000   ns        3 us
Send 1K bytes over 1 Gbps network       10,000   ns       10 us
Read 4K randomly from SSD*             150,000   ns      150 us          ~1GB/sec SSD