Vikas Raunak vyraun

##VGG19 model for Keras

This is the Keras model of the 19-layer network used by the VGG team in the ILSVRC-2014 competition.

It has been obtained by directly converting the Caffe model provived by the authors.

Details about the network architecture can be found in the following arXiv paper:

Very Deep Convolutional Networks for Large-Scale Image Recognition

K. Simonyan, A. Zisserman

A very opinionated Python getting-started guide

Start by subscribing to Python Weekly mailinglist. Good overview of new projects, libraries, etc.
Depending on your programming experience, skip/skim/follow/study a course book. For free/online, you have for instance,
- Dive Into Python which is example-heavy & aimed at people with some programming background.
- How To Think Like a Computer Scientist starts more from scratch, and is also used in an introductory programming MIT OCW course for electrical engineering students if you want video lectures/excercises/exams.

Setup your Python packages environment

Install globally pip, package manager for Python packages.

##Model

This is an implementation of Facebook's baseline GRU/LSTM model on the bAbI dataset Weston et al. 2015. It includes an interactive demo.

The bAbI dataset contains 20 different question answering tasks.

Model script

The model training script train.py and demo script demo.py are included below.

Instructions

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

ffmpeg

Converting Audio into Different Formats / Sample Rates

Minimal example: transcode from MP3 to WMA:
ffmpeg -i input.mp3 output.wma

You can get the list of supported formats with:
ffmpeg -formats

You can get the list of installed codecs with:


	def binary_crossentropy_with_ranking(y_true, y_pred):
	""" Trying to combine ranking loss with numeric precision"""
	# first get the log loss like normal
	logloss = K.mean(K.binary_crossentropy(y_pred, y_true), axis=-1)

	# next, build a rank loss

	# clip the probabilities to keep stability
	y_pred_clipped = K.clip(y_pred, K.epsilon(), 1-K.epsilon())

	raise ValueError("DEPRECATED/FROZEN - see https://github.com/kastnerkyle/tools for the latest")

	# License: BSD 3-clause
	# Authors: Kyle Kastner
	# Harvest, Cheaptrick, D4C, WORLD routines based on MATLAB code from M. Morise
	# http://ml.cs.yamanashi.ac.jp/world/english/
	# MGC code based on r9y9 (Ryuichi Yamamoto) MelGeneralizedCepstrums.jl
	# Pieces also adapted from SPTK
	from __future__ import division
	import numpy as np

	# coding: utf-8
	from __future__ import division

	import struct
	import sys

	FILE_NAME = "GoogleNews-vectors-negative300.bin"
	MAX_VECTORS = 200000 # This script takes a lot of RAM (>2GB for 200K vectors), if you want to use the full 3M embeddings then you probably need to insert the vectors into some kind of database
	FLOAT_SIZE = 4 # 32bit float

	"""
	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)

	import threading
	import time


	class ThreadingExample(object):
	""" Threading example class

	The run() method will be started and it will run in the background
	until the application exits.
	"""