Skip to content

Instantly share code, notes, and snippets.

View darkseed's full-sized avatar

Tom Mulder darkseed

37 followers · 82 following
View GitHub Profile
@darkseed
darkseed / Backend Architectures Keywords and References.md
Created March 9, 2016 14:38 — forked from ragingwind/Backend Architectures Keywords and References.md
Backend Architectures Keywords and References
@darkseed
darkseed / Cooccurrence Analysis Prototype
Created January 15, 2016 11:43 — forked from sscdotopen/Cooccurrence Analysis Prototype
package org.apache.spark.examples
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.rdd.RDD
import java.util.Random
import scala.collection.mutable
import org.apache.spark.serializer.KryoRegistrator
import com.esotericsoftware.kryo.Kryo
@darkseed
darkseed / MovieSimilarities.scala
Created December 8, 2015 14:29 — forked from MLnick/MovieSimilarities.scala
Movie Similarities with Spark
import spark.SparkContext
import SparkContext._
/**
* A port of [[http://blog.echen.me/2012/02/09/movie-recommendations-and-more-via-mapreduce-and-scalding/]]
* to Spark.
* Uses movie ratings data from MovieLens 100k dataset found at [[http://www.grouplens.org/node/73]]
*/
object MovieSimilarities {
@darkseed
darkseed / fc7 code generation.ipynb
Created November 25, 2015 13:25 — forked from kylemcdonald/fc7 code generation.ipynb
Generating fc7-layer codes from one-hot prob-layer activations.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@darkseed
darkseed / Class similarity.ipynb
Created November 25, 2015 13:22 — forked from kylemcdonald/Class similarity.ipynb
Finding similarities with a neural network that trained for object classification.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@darkseed
darkseed / Audio Autoencoder.ipynb
Created November 25, 2015 13:21 — forked from kylemcdonald/Audio Autoencoder.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@darkseed
darkseed / rank_metrics.py
Created November 23, 2015 15:11 — forked from bwhite/rank_metrics.py
Ranking Metrics
"""Information Retrieval metrics
Useful Resources:
http://www.cs.utexas.edu/~mooney/ir-course/slides/Evaluation.ppt
http://www.nii.ac.jp/TechReports/05-014E.pdf
http://www.stanford.edu/class/cs276/handouts/EvaluationNew-handout-6-per.pdf
http://hal.archives-ouvertes.fr/docs/00/72/67/60/PDF/07-busa-fekete.pdf
Learning to Rank for Information Retrieval (Tie-Yan Liu)
"""
import numpy as np
@darkseed
darkseed / VGG_ILSVRC_19_layers_train_val.prototxt
Created October 20, 2015 20:43 — forked from graphific/VGG_ILSVRC_19_layers_train_val.prototxt
VGG_ILSVRC_19_layers_train_val.prototxt
name: "VGG_ILSVRC_19_layers"
layers {
name: "data"
type: DATA
include {
phase: TRAIN
}
transform_param {
crop_size: 224
@darkseed
darkseed / mr_compute_gist.py
Created October 18, 2015 20:05 — forked from Yangqing/mr_compute_gist.py
The mapreduce code to extract gist features from ImageNet images. To be used together with mincepie.
from mincepie import mapreducer, launcher
import gflags
import glob
import leargist
import numpy as np
import os
from PIL import Image
import uuid
# constant value
@darkseed
darkseed / BloomFilter2.scala
Created October 7, 2015 09:59
class BloomFilter(val size: Int, val expectedElements: Int){
require(size > 0)
require(expectedElements > 0)
val bitArray = new BitArray(size)
val k = Math.ceil((bitArray.size / expectedElements) * Math.log(2.0)).toInt
val expectedFalsePositiveProbability = Math.pow(1 - Math.exp(-k * 1.0 * expectedElements / bitArray.size), k)
def add(hash: Int) {
def add(i: Int, seed: Int) {