hengrumay

Instructions for making a Neural-Style movie

The following instructions are for creating your own animations using the style transfer technique described by Gatys, Ecker, and Bethge, and implemented by Justin Johnson. To see an example of such an animation, see this video of Alice in Wonderland re-styled by 17 paintings.

Setting up the environment

The easiest way to set up the environment is to simply load Samim's a pre-built Terminal.com snap or use another cloud service like Amazon EC2. Unfortunately the g2.2xlarge GPU instances cost $0.99 per hour, and depending on parameters selected, it may take 10-15 minutes to produce a 512px-wide image, so it can cost $2-3 to generate 1 sec of video at 12fps.

If you do load the

do androids dream of cooking?

The following recipes are sampled from a trained neural net. You can find the repo to train your own neural net here: https://github.com/karpathy/char-rnn Thanks to Andrej Karpathy for the great code! It's really easy to setup.

The recipes I used for training the char-rnn are from a recipe collection called ffts.com And here is the actual zipped data (uncompressed ~35 MB) I used for training. The ZIP is also archived @ archive.org in case the original links becomes invalid in the future.

Architectural Questions

Are responsibilities well defined?
Are the collaborations well defined?
Is coupling minimized?
Can you identify potential duplication?
Are interface definitions and constraints acceptable?
Can modules access needed data—when needed?

	# -- coding: utf-8 --

	import sys
	import numpy

	numpy.seterr(all='ignore')


	'''

	"""
	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)

	"""
	A script to take all of the LineString information out of a very large KML file. It formats it into a CSV file so
	that you can import the information into the NDB of Google App Engine using the Python standard library. I ran this
	script locally to generate the CSV. It processed a ~70 MB KML down to a ~36 MB CSV in about 8 seconds.

	The KML had coordinates ordered by
	[Lon, Lat, Alt, ' ', Lon, Lat, Alt, ' ',...] (' ' is a space)
	The script removes the altitude to put the coordinates in a single CSV row ordered by
	[Lat,Lon,Lat,Lon,...]

	from IPython.display import display, HTML

	display(HTML(data="""
	<style>
	div#notebook-container { width: 95%; }
	div#menubar-container { width: 65%; }
	div#maintoolbar-container { width: 99%; }
	</style>
	"""))

	wget https://www.python.org/ftp/python/3.4.2/Python-3.4.2.tgz
	tar zxvf Python-3.4.2.tgz
	cd Python-3.4.2
	sudo yum install gcc
	./configure --prefix=/opt/python3
	make
	sudo make install
	sudo ln -s /opt/python3/bin/python3 /usr/bin/python3
	sudo ln -s /opt/python3/bin/easy_install-3.4 /usr/bin/easy_install3
	sudo ln -s /opt/python3/bin/pip3 /usr/bin/pip3.4

	import pyaudio
	import wave
	import audioop
	from collections import deque
	import os
	import urllib2
	import urllib
	import time
	import math
	import json