leotam

Introduction

GraphLab abstraction exposes asynchronous, dynamic, graph-parallel computation model in the shared-memory setting.
This paper extends the abstraction to the distributed setting.
Link to the paper.

Characteristics of MLDM (Machine Learning and Data Mining)

Graph Structured Computation
Sometimes computation requires modeling dependencies between data.

Introduction

This project makes a wifi router out of an ASUS PCE-AC88 wireless adapter and your Ubuntu Linux computer that can exceed top of the line routers.

Instead of buying a gaming grade router or another computer that you install openWRT on, follow this project and put the savings towards upgrading your main computer or modem.

Add Adapter

The adapter needs to be added to a PCI slot and the wireless antenna needs to be connected to the adapter. If your computer does not detect it, you may need to re-seat the adapter in the slot. If you can't detect wireless networks after installing the firmware below then this is probably why.

Install Firmware for Adapter

For your computer to use the wifi adapter you need to add the missing firmware that Asus won't provide.

	sudo yum -y install epel-release
	sudo yum -y install gcc gcc-c++ python-pip python-devel atlas atlas-devel gcc-gfortran openssl-devel libffi-devel
	# use pip or pip3 as you prefer for python or python3
	pip install --upgrade virtualenv
	virtualenv --system-site-packages ~/venvs/tensorflow
	source ~/venvs/tensorflow/bin/activate
	pip install --upgrade numpy scipy wheel cryptography #optional
	pip install --upgrade https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.10.0rc0-cp35-cp35m-linux_x86_64.whl
	# or below if you want gpu, support, but cuda and cudnn are required, see docs for more install instructions
	pip install --upgrade https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow-0.10.0rc0-cp35-cp35m-linux_x86_64.whl

	/*
	Comparing explicit BLAS parallelism using a thread pool
	with vendor-implemented parallelism.

	Program prints the runtime averaged over 100 runs of a matrix
	multiply between two float matrices.

	To run:

	./gemm_parallel [<int> USE_EXPLICIT_PARALELLISM 0/1] [<int> LEADING_DIMENSION]

	# Implementation of a rotating buffer on the GPU of size 2.
	import threading
	import tensorflow as tf
	from tensorflow.python.client import timeline
	import numpy as np
	import time

	params = {
	'batch_size': 128,
	'seg_len': 4000,

	# Gist example of IB wrapper ...
	#
	# Download API from http://interactivebrokers.github.io/#
	#
	# Install python API code /IBJts/source/pythonclient $ python3 setup.py install
	#
	# Note: The test cases, and the documentation refer to a python package called IBApi,
	# but the actual package is called ibapi. Go figure.
	#
	# Get the latest version of the gateway:

	# See "Self-Normalizing Neural Networks" https://arxiv.org/abs/1706.02515
	# "SNNs cannot be derived with...tanh units..."
	# So I'm probably missing the point somewhere...

	import math
	import numpy

	# Magic number
	lambda0 = 1.59254

	"""
	Create train, valid, test iterators for CIFAR-10 [1].
	Easily extended to MNIST, CIFAR-100 and Imagenet.

	[1]: https://discuss.pytorch.org/t/feedback-on-pytorch-for-kaggle-competitions/2252/4
	"""

	import torch
	import numpy as np

	''' Script for downloading all GLUE data.

	Note: for legal reasons, we are unable to host MRPC.
	You can either use the version hosted by the SentEval team, which is already tokenized,
	or you can download the original data from (https://download.microsoft.com/download/D/4/6/D46FF87A-F6B9-4252-AA8B-3604ED519838/MSRParaphraseCorpus.msi) and extract the data from it manually.
	For Windows users, you can run the .msi file. For Mac and Linux users, consider an external library such as 'cabextract' (see below for an example).
	You should then rename and place specific files in a folder (see below for an example).

	mkdir MRPC
	cabextract MSRParaphraseCorpus.msi -d MRPC