j-min

Freshly brewed !

With the availability of huge amount of data for research and powerfull machines to run your code on, Machine Learning and Neural Networks is gaining their foot again and impacting us more than ever in our everyday lives. With huge players like Google opensourcing part of their Machine Learning systems like the TensorFlow software library for numerical computation, there are many options for someone interested in starting off with Machine Learning/Neural Nets to choose from. Caffe, a deep learning framework developed by the Berkeley Vision and Learning Center (BVLC) and its contributors, comes to the play with a fresh cup of coffee.

Installation Instructions (Ubuntu 14 Trusty)

The following section is divided in to two parts. Caffe's documentation suggest

j-min

# https://github.com/mps-youtube/pafy
import pafy

if __name__ == '__main__':
    video_url = 'https://www.youtube.com/watch?v=D_Ij3fAps4s'
    video = pafy.new(video_url)
    print(video.title, video.duration)

    best = video.getbest()
    best.download(quiet=False)

j-min

# pip install korail2
# https://github.com/carpedm20/korail2

from korail2 import Korail, NoResultsError, KorailError
from time import sleep
import os

# Login
EMAIL = '' # email
PW = '' # password

j-min

TMUX_VERSION=2.6

cd $HOME

# Dependencies
sudo apt install libevent-dev ncurses-dev -y

# Download tmux
wget https://github.com/tmux/tmux/releases/download/$TMUX_VERSION/tmux-$TMUX_VERSION.tar.gz
tar -xvzf tmux-$TMUX_VERSION.tar.gz

j-min

# http://pytorch.org/tutorials/beginner/transfer_learning_tutorial.html

def exp_lr_scheduler(optimizer, epoch, init_lr=0.001, lr_decay_epoch=7):
    """Decay learning rate by a factor of 0.1 every lr_decay_epoch epochs."""
    lr = init_lr * (0.1**(epoch // lr_decay_epoch))

    if epoch % lr_decay_epoch == 0:
        print('LR is set to {}'.format(lr))

    for param_group in optimizer.param_groups:

j-min

import matplotlib

# font configuration
matplotlib.rc('font', family='NanumGothic', size=22)

j-min

from IPython.display import clear_output, Image, display, HTML
import numpy as np

def strip_consts(graph_def, max_const_size=32):
    """Strip large constant values from graph_def."""
    strip_def = tf.GraphDef()
    for n0 in graph_def.node:
        n = strip_def.node.add() 
        n.MergeFrom(n0)
        if n.op == 'Const':

j-min

j-min

ZSH=$HOME/.zsh

HISTFILE=$HOME/.history
HISTSIZE=10000
SAVEHIST=10000

export TERM=xterm-256color
export LANG=en_US.UTF-8
# added by Anaconda3 4.1.1 installer
export PATH=$HOME/anaconda3/bin:$PATH

j-min

import math

def convertSize(size):
	"""
	Return filesize (in Bytes) in human-readable format
	"""
	if (size == 0):
		return '0B'
	units = ("B", "KB", "MB", "GB", "TB", "PB", "EB", "ZB", "YB")
	i = int(math.floor(math.log(size,1024)))