akatumba’s gists

akatumba / sgdr.py

Created June 30, 2018 11:44 — forked from jeremyjordan/sgdr.py

Keras Callback for implementing Stochastic Gradient Descent with Restarts

	from keras.callbacks import Callback
	import keras.backend as K
	import numpy as np

	class SGDRScheduler(Callback):
	'''Cosine annealing learning rate scheduler with periodic restarts.

	# Usage
	```python
	schedule = SGDRScheduler(min_lr=1e-5,

akatumba / lamp.sh

Created March 14, 2018 09:39 — forked from aamnah/lamp.sh

Bash script to install Apache, MySQL and PHP as well as PHPMyAdmin and some tweaks. For Debian and Ubuntu. To run, copy the script to the server and run ``bash lamp.sh``

	#!/bin/sh

	#######################################
	# Bash script to install an AMP stack and PHPMyAdmin plus tweaks. For Debian based systems.
	# Written by @AamnahAkram from http://aamnah.com

	# In case of any errors (e.g. MySQL) just re-run the script. Nothing will be re-installed except for the packages with errors.
	#######################################

	#COLORS

akatumba / bitbucket-pipelines.yml

Created February 13, 2018 14:12 — forked from adujardin/bitbucket-pipelines.yml

Bitbucket pipeline file for latex document (including bibtex and upload to dropbox)

	# SETTING UP :
	# Generate an application token for your dropbox account and set it as environment variable named "DROPBOX_TOKEN"
	# - https://blogs.dropbox.com/developers/2014/05/generate-an-access-token-for-your-own-account/
	# - https://confluence.atlassian.com/bitbucket/environment-variables-794502608.html
	# Edit TEX_FILE (see below) according to the main tex file name

	image: fermiumlabs/latex-docker:latest

	pipelines:
	custom: # Manually only

akatumba / install.sh

Created November 29, 2017 21:23

VPS install bash script for Ubuntu 16.04


	# =================== YOUR DATA ========================

	SERVER_NAME="some-server-name"
	SERVER_IP="111.111.11.11"

	USER="someuser"
	SUDO_PASSWORD="secret-password-one"
	MYSQL_ROOT_PASSWORD="secret-password-two"

akatumba / min-char-rnn.py

Created January 21, 2017 16:20 — forked from karpathy/min-char-rnn.py

Minimal character-level language model with a Vanilla Recurrent Neural Network, in Python/numpy

	"""
	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)

akatumba / sincinterpol.py

Created April 13, 2016 18:42 — forked from gauteh/sincinterpol.py

sinc interpolation of signal using numpy / python: http://scipy-central.org/item/99/1/sinc-interpolation-of-signal-using-numpy-python

	#! /usr/bin/python
	#
	# Author: Gaute Hope (gaute.hope@nersc.no) / 2015
	#
	# based on example from matlab sinc function and
	# interpolate.m by H. Hobæk (1994).
	#
	# this implementation is similar to the matlab sinc-example, but
	# calculates the values sequentially and not as a single matrix
	# matrix operation for all the values.

akatumba / pyspark

Last active August 29, 2015 14:18

pyspark LogisticRegressionWithSGD

	from pyspark.mllib.classification import LogisticRegressionWithSGD
	from pyspark.mllib.regression import LabeledPoint
	from numpy import array #not used

	#use sample data provided in the mllib installation
	data = sc.textFile('data/mllib/sample_svm_data.txt')

	#convert the data into the format expected by the regression model trainer
	parsedData = data.map(lambda line: LabeledPoint(line.split(' ')[0], line.split(' ')[1:]))