soumith

require 'image'
local memTestClass = torch.class('image.memTestClass')
function memTestClass:__newindex__(key, value)
   if type(key) == 'number' then 
      return 1 -- do this so that rawset isn't called anyways, stupid of me to miss this
   else rawset(self, key, value) end
end

function testMemory()
   n = 50000

soumith

#!/usr/bin/env torch
require 'nn'
require 'image'
require 'xlua'
require 'pl'


opt = lapp[[
		 -t,--threads            (default 8)           number of threads
   -p,--type               (default float)       float or cuda

soumith

local async = require 'async'
local http = require 'socket.http'
local ltn12 = require 'ltn12'

function start()
   local url = 'tcp://localhost:8082/'
   while true do
      print(os.date())

      local response = {}

soumith

local tcp = require 'socket'
require 'sys'

function start()
   while true do
      print(os.date())
      local conn = tcp.connect('localhost',8483)
      conn:send('ealasjdiasldjeladj')
      conn:close()
      sys.sleep(0.01)

soumith

features = nn.Sequential()
features:add(nn.Transpose({1,4},{1,3},{1,2}))
features:add(nn.SpatialConvolutionCUDA(fSize[1], fSize[2], 9, 9, 2, 2)) -- (111 - 9 + 2)/2 = 52
features:add(nn.Threshold(0,1e-6))
features:add(nn.SpatialMaxPoolingCUDA(2,2,2,2)) -- 26
features:add(nn.SpatialConvolutionCUDA(fSize[2], fSize[3], 5, 5)) -- 22
features:add(nn.Threshold(0,1e-6))
features:add(nn.SpatialMaxPoolingCUDA(2,2,2,2)) -- 11
features:add(nn.SpatialConvolutionCUDA(fSize[3], fSize[4], 4, 4)) -- 8
features:add(nn.Threshold(0,1e-6))

soumith

require 'torch'
require 'nn'


local mytester = torch.Tester()
local precision = 1e-5

local critest = {}

function critest.MSECriterion()

soumith

require 'torch'
require 'nn'

torch.setdefaulttensortype('torch.FloatTensor')
-------------- Model -------------------------
branch = nn.Sequential()
branch:add(nn.Linear(4,5))
branch:add(nn.Linear(5,1))

parallel=nn.Parallel(1,1);

soumith

require 'torch'
require 'nn'
 
torch.setdefaulttensortype('torch.FloatTensor')

frameSize = 4 -- each input frame has 4 numbers
hiddenSize = 5 -- each hidden layer has 5 units
outputSize = 1 -- each output layer has 1 output
-------------- Model -------------------------
mlp = nn.Sequential()

soumith

require 'torch'
require 'nn'
require 'sys'

torch.setdefaulttensortype('torch.FloatTensor')
numInputNodes=30
numBatches=64
numHidden1=64
numHidden2=128
numOutputNodes=1

soumith

dataset=torch.Tensor{
   {742313794,6385273,1362403386,80,169085576,0,1698277100,451,0},
   {742313860,6385273,1362403386,80,169085576,0,1698300945,452,0},
   {742338872,6385273,167840643,137,169085576,0,1718221933,480,0},
   {742338872,6385273,167926801,53,169085576,0,1718222057,471,0},
   {742338872,6385273,167846975,8014,169085576,0,1718222380,487,0},
   {742338872,641958438357784123396879472047392017641614042483,167846975,8014,169085576,0,1718222453,517,0},
   {742338934,6385273,167926801,53,169085576,0,1718273961,472,0},
   {742338934,641958438357784123396879472047392017641614042483,167846975,8014,169085576,0,1718275304,519,0},
   {742338934,6385273,167840643,137,169085576,0,1718275541,483,0},