jhjin

require('image')

local function iterate(src)
   for dir in paths.iterdirs(src) do
      local subdir = path.join(src, dir)
      print(subdir)
      for file in paths.iterfiles(subdir) do
         local filepath = path.join(subdir, file)
         local ok, img = pcall(image.loadJPG, filepath, 3, 'float')
         if not ok then

jhjin

#include <stdio.h>
#include <stdlib.h>


// CUDA: grid stride looping
#define CUDA_KERNEL_LOOP(i, n) \
   for (int i = blockIdx.x * blockDim.x + threadIdx.x; i < (n); i += blockDim.x * gridDim.x)

// Use 1024 threads per block, which requires cuda sm_2x or above
const int CUDA_NUM_THREADS = 1024;

jhjin

torch.setdefaulttensortype('torch.FloatTensor')

require('torch')
require('pl')
require('nn')
require('cunn')
require('cudnn')


local opt = lapp([[

jhjin

#!/usr/bin/env th
--
-- *Face alignment on dataset
--
--   For given (source dataset) path, it traverses all subdirectories and
--   align/crop faces from all images and save them in the destination path.
--
-- Author: Jonghoon Jin
--
require('pl')

jhjin

require('pl')
require('xlua')
require('image')
local dir = require('pl.dir')
local path = require('pl.path')


local opt = lapp([[
Required parameters
   --src            (default '.')     path for source image root directory

jhjin

# Download IEEE article via a server that has IEEE text access (Usage: $ ieee 5738219)
function ieee() {
  local cmd="'wget \"http://ieeexplore.ieee.org/stampPDF/getPDF.jsp?tp=&isnumber=&arnumber=${@}\" -O paper.pdf'"
  ssh elab5 eval ${cmd}
  scp elab5:~/paper.pdf $@.pdf
  ssh elab5 'rm -f paper.pdf'
}

jhjin

#!/usr/bin/bash
iterator=1
url="http://www.deeplearningbook.org/contents/"
array=(
   TOC.html
   acknowledgements.html
   notation.html
   intro.html
   part_basics.html 
   linear_algebra.html

jhjin

## Refer to http://caffe.berkeleyvision.org/installation.html
# Contributions simplifying and improving our build system are welcome!

# cuDNN acceleration switch (uncomment to build with cuDNN).
# USE_CUDNN := 1

# CPU-only switch (uncomment to build without GPU support).
CPU_ONLY := 1

# uncomment to disable IO dependencies and corresponding data layers

jhjin

brew install python
brew install wget
brew install protobuf
brew install boost-python
brew install lmdb
brew install leveldb
brew install snappy
brew install gflags
brew install glog
brew tap homebrew/science

jhjin

#!/usr/bin/env python
import numpy as np
import matplotlib.pyplot as plt
import caffe
caffe.set_mode_cpu()


path_src = 'src.caffemodel'
path_dst = 'dst.caffemodel'
net_src = caffe.Net('src.prototxt', path_src, caffe.TEST)