Jeong Hyunseok nicewook

## rnn_tutorial_.idea_misc.xml
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.5.2 (C:\Program Files\Anaconda3\python.exe)" project-jdk-type="Python SDK" />
</project>

## min-char-rnn.py
"""
Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
BSD License
"""
import numpy as np

# data I/O
data = open('input.txt', 'r').read() # should be simple plain text file
chars = list(set(data))
data_size, vocab_size = len(data), len(chars)

## mdn_toy.py
# 원문링크: http://blog.otoro.net/2015/11/24/mixture-density-networks-with-tensorflow/

##############################################################
# 라이브러리 import
##############################################################

import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
import math

## lab-11-2-mnist_deep_cnn_jhs.py
# Lab 10 MNIST and Deep learning CNN
'''
모두의딥러닝 lab-11-2 기반으로 짜보았습니다.
생각한 컨셉은 다음과 같습니다.

1. training을 돌려서 accuracy가 70%가 넘으면 멈춘다
2. 예측이 틀린 train set의 label을 +10 해준다 - 별도로 분류해보겠다는 것이었습니다.
3. 모든 Weights, biases 를 초기화 한 다음 다시 training 한다
4. 이렇게 학습시킨 네트웍으로 test set을 검증한다 - 물론 검증시 10보다 큰 예측은 -10 해준다

## Spatial_Transformer_Example_Part1.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                nicewook
                / Spatial_Transformer_Example_Part1.ipynb
            
            
              Created
              April 27, 2017 14:50
                — forked from kvn219/Spatial_Transformer_Example_Part1.ipynb
            
              
                Spatial Transformer Networks with Tensorflow: Part I
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## rnn_tutorial-Copy2.ipynb

      
              1 file
            
          
              2 forks
            
          
              0 comments
            
          
              0 stars
            
          
                nicewook
                / rnn_tutorial-Copy2.ipynb
            
            
              Created
              June 7, 2017 03:05
            
              
                rnn toy code - korean comment
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## spacosa.sh
#!/bin/bash
#this is for tmux session initialize set script
SESSION_NAME="spacosa"

# check if session already exist
if(tmux has-session -t $SESSION_NAME 2> /dev/null); then
	echo "Session $SESSION_NAME exists"
else
	echo "Session $SESSION_NAME not exist. Create one"
	tmux -2 new-session -s ${SESSION_NAME} -d  # -2 means 256 color

## count_light.py
// code from Hwang Hae Yeon of My Facebook Friend
// Count light from the photo of night scenary

import numpy as np
import argparse
import cv2

def is_contour (c):
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.02 * peri, True)

## move_to_sub_directories.sh
#!/bin/bash

c=1; d=1; mkdir -p dir_${d}

for file in *
do
        if [ $c -eq 3001 ]
        then
                d=$(( d + 1 )); c=0; mkdir -p dir_${d}
        fi

## move all files to sub directories
#!/bin/bash

c=0; d=0; mkdir -p data${d}

for file in ./test/*
do
        if [ $c -eq 10000 ]
        then
                d=$(( d + 1 )); c=0; mkdir -p data${d}
        fi
	<?xml version="1.0" encoding="UTF-8"?>
	<project version="4">
	<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.5.2 (C:\Program Files\Anaconda3\python.exe)" project-jdk-type="Python SDK" />
	</project>
	"""
	Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
	BSD License
	"""
	import numpy as np

	# data I/O
	data = open('input.txt', 'r').read() # should be simple plain text file
	chars = list(set(data))
	data_size, vocab_size = len(data), len(chars)
	# 원문링크: http://blog.otoro.net/2015/11/24/mixture-density-networks-with-tensorflow/

	##############################################################
	# 라이브러리 import
	##############################################################

	import matplotlib.pyplot as plt
	import numpy as np
	import tensorflow as tf
	import math
	# Lab 10 MNIST and Deep learning CNN
	'''
	모두의딥러닝 lab-11-2 기반으로 짜보았습니다.
	생각한 컨셉은 다음과 같습니다.

	1. training을 돌려서 accuracy가 70%가 넘으면 멈춘다
	2. 예측이 틀린 train set의 label을 +10 해준다 - 별도로 분류해보겠다는 것이었습니다.
	3. 모든 Weights, biases 를 초기화 한 다음 다시 training 한다
	4. 이렇게 학습시킨 네트웍으로 test set을 검증한다 - 물론 검증시 10보다 큰 예측은 -10 해준다
	#!/bin/bash
	#this is for tmux session initialize set script
	SESSION_NAME="spacosa"

	# check if session already exist
	if(tmux has-session -t $SESSION_NAME 2> /dev/null); then
	echo "Session $SESSION_NAME exists"
	else
	echo "Session $SESSION_NAME not exist. Create one"
	tmux -2 new-session -s ${SESSION_NAME} -d # -2 means 256 color
	// code from Hwang Hae Yeon of My Facebook Friend
	// Count light from the photo of night scenary

	import numpy as np
	import argparse
	import cv2

	def is_contour (c):
	peri = cv2.arcLength(c, True)
	approx = cv2.approxPolyDP(c, 0.02 * peri, True)
	#!/bin/bash

	c=1; d=1; mkdir -p dir_${d}

	for file in *
	do
	if [ $c -eq 3001 ]
	then
	d=$(( d + 1 )); c=0; mkdir -p dir_${d}
	fi
	#!/bin/bash

	c=0; d=0; mkdir -p data${d}

	for file in ./test/*
	do
	if [ $c -eq 10000 ]
	then
	d=$(( d + 1 )); c=0; mkdir -p data${d}
	fi