Dixing (Dex) Xu dexhunter

tmux shortcuts & cheatsheet

start new:

tmux

start new with session name:

tmux new -s myname

The Batch Normalization paper describes a method to address the various issues related to training of Deep Neural Networks. It makes normalization a part of the architecture itself and reports significant improvements in terms of the number of iterations required to train the network.

Issues With Training Deep Neural Networks

Internal Covariate shift

Covariate shift refers to the change in the input distribution to a learning system. In the case of deep networks, the input to each layer is affected by parameters in all the input layers. So even small changes to the network get amplified down the network. This leads to change in the input distribution to internal layers of the deep network and is known as internal covariate shift.

It is well established that networks converge faster if the inputs have been whitened (ie zero mean, unit variances) and are uncorrelated and internal covariate shift leads to just the opposite.

##VGG16 model for Keras

This is the Keras model of the 16-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

	""" Module to compute projections on the positive simplex or the L1-ball

	A positive simplex is a set X = { \mathbf{x} \| \sum_i x_i = s, x_i \geq 0 }

	The (unit) L1-ball is the set X = { \mathbf{x} \| \|\| x \|\|_1 \leq 1 }

	Adrien Gaidon - INRIA - 2011
	"""

	import math
	from dbfpy import dbf
	import matplotlib.pyplot as plt

	#create a plot
	fig = plt.figure(1, figsize = [10,10], dpi=90)
	axScatter = plt.subplot(111)

	def candMedian(dataPoints):
	#Calculate the first candidate median as the geometric mean

	# Exit on error #
	set -e

	# Clean up #
	rm -rf ~/tools/programs/libevent
	rm -rf ~/tools/programs/ncurses
	rm -rf ~/tools/programs/tmux

	# Variable version #
	TMUX_VERSION=2.2

	#!/bin/sh

	git filter-branch --env-filter '

	OLD_EMAIL="[email protected]"
	CORRECT_NAME="Your Correct Name"
	CORRECT_EMAIL="[email protected]"

	if [ "$GIT_COMMITTER_EMAIL" = "$OLD_EMAIL" ]
	then

	""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
	import numpy as np
	import cPickle as pickle
	import gym

	# hyperparameters
	H = 200 # number of hidden layer neurons
	batch_size = 10 # every how many episodes to do a param update?
	learning_rate = 1e-4
	gamma = 0.99 # discount factor for reward

	// Use Gists to store code you would like to remember later on
	console.log(window); // log the "window" object to the console

	# On Ubuntu 14.04 with Titan X (compute capability 5.2)
	# There are some missing parts that you have to specify, and some files you have to download manaully from web, so don't run this script file as it is.
	# Configure CUDA paths
	echo export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/cuda/lib64" >> ~/.bashrc
	echo export CUDA_HOME="/usr/local/cuda" >> ~/.bashrc
	source ~/.bashrc

	# Set up java
	# Dependencies for Bazel
	# Download jdk 8