culurciello

#!/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

culurciello

local cv = require 'cv'
require 'cv.highgui'
require 'cv.imgproc'
require 'cv.imgcodecs'
require 'image'

-- local image = cv.imread{arg[1] or 'demo/lena.jpg', cv.IMREAD_GRAYSCALE}
imgT = image.lena()
imgT = image.lena()
imgTg = imgT[2] -- convert to grayscale and remove the first dimension

culurciello

/*
Test of C code speed with Apple Accelerate Framework and openmp
https://developer.apple.com/library/mac/documentation/Accelerate/Reference/BLAS_Ref/Reference/reference.html#//apple_ref/c/func/cblas_sgemm
compile with: 
gcc -Ofast -fopenmp -flax-vector-conversions -framework Accelerate acctest.c 
*/
 
#include <stdio.h>
#include <stdlib.h>
#include <fcntl.h>

culurciello

/*
Test of C code speed
compile with: gcc -Ofast -fopenmp -mavx mactest.c
or gfortran -O3 -fopenmp mactest.c 
*/
 
#include <stdio.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/time.h>

culurciello

to resize 1080p videos:
ffmpeg -i pool.mp4 -vf scale=640:360 pool-small.mp4

to match odroid fps (12fps): need to speed up video:
https://trac.ffmpeg.org/wiki/How%20to%20speed%20up%20/%20slow%20down%20a%20video
1:
ffmpeg -i dog.mp4 -vf scale=640:360 -filter:v "setpts=0.5*PTS" dog-2x.mp4
because it does not scale with this command, so we need to do more:
2:

culurciello

My Unix shortcuts and tips

• Bash
• Git
• Vim
  • Vimdidd
• Tmux
• Mac

Bash

culurciello

--------------------------------------------------------------------------------
-- E. Culurciello SSD speed test for batch 128
-------------------------------------------------------------------------------

print('SSD test program in for Torch7 batches')

torch.manualSeed(1)
torch.setdefaulttensortype('torch.FloatTensor')
torch.setnumthreads(8)

culurciello

   local mask = function (inputImage, mask, th)
      local temp
      mask = mask[1]
      k = image.gaussian{size = 7, normalize = true}:float()
      mask = image.convolve(mask, k, 'same'):repeatTensor(3,1,1)
      temp = mask:gt(th):float():mul(.8):add(.2)

      return inputImage:clone():cmul(temp)
   end

culurciello

-- net cpu/gpu speed test
-- E. Culurciello, March 2015

require 'nn'
require('cunn')

torch.setdefaulttensortype('torch.FloatTensor')
net = torch.load('../../models/home-A1l/model.net')
net_gpu = torch.load('../../models/home-A1l/model.net')
net_gpu:cuda()

culurciello

--[[ precision-test

Compare precision of hardware and software implementation
run with: qlua precision-network.lua

--]]

require 'nn'
require 'pl'
require 'image'