nzw0301

*2vec papers

1. act2vec, trace2vec, log2vec, model2vec https://link.springer.com/chapter/10.1007/978-3-319-98648-7_18
2. apk2vec https://arxiv.org/abs/1809.05693
3. app2vec http://paul.rutgers.edu/~qma/research/ma_app2vec.pdf
4. ast2vec https://arxiv.org/abs/2103.11614
5. attribute2vec https://arxiv.org/abs/2004.01375
6. author2vec http://dl.acm.org/citation.cfm?id=2889382
7. baller2vec https://arxiv.org/abs/2102.03291
8. bb2vec https://arxiv.org/abs/1809.09621

brannondorsey

Image-to-Image Translation with Conditional Adversarial Networks

Notes from arXiv:1611.07004v1 [cs.CV] 21 Nov 2016

• Euclidean distance between predicted and ground truth pixels is not a good method of judging similarity because it yields blurry images.
• GANs learn a loss function rather than using an existing one.
• GANs learn a loss that tries to classify if the output image is real or fake, while simultaneously training a generative model to minimize this loss.
• Conditional GANs (cGANs) learn a mapping from observed image x and random noise vector z to y: y = f(x, z)
• The generator G is trained to produce outputs that cannot be distinguished from "real" images by an adversarially trained discrimintor, D which is trained to do as well as possible at detecting the generator's "fakes".
• The discriminator D, learns to classify between real and synthesized pairs. The generator learns to fool the discriminator.
• Unlike an unconditional GAN, both th

durden

##### Taken from https://github.com/bosswissam/pysize

import sys

def get_size(obj, seen=None):
    """Recursively finds size of objects"""

    size = sys.getsizeof(obj)
    if seen is None:
        seen = set()

itod

• Kinesis Freestyle (Terrible key switches. Mushy and un-lovable)

• Kinesis Freestyle Edge (Traditional layout with too many keys, mech switches, proably too big to be tented easily/properly)

• Matias Ergo Pro (Looks pretty great. Have not tried.)

• ErgoDox Kit (Currently, my everyday keyboard. Can buy pre-assembled on eBay.)

• ErgoDox EZ (Prolly the best option for most people.)

haje01

분산 텐서플로우

이 글을 작성하는 시점(2017-01-11)에서 분산 텐서플로우의 관련 자료 부족으로 확실히 분산 학습이 되는지 확인이 되지 않았습니다. 안타깝지만 본 내용은 참고만 하시기 바랍니다.

원문 [https://www.tensorflow.org/how_tos/distributed/] (https://www.tensorflow.org/how_tos/distributed/)

개념 설명

• 클러스터는 텐서플로우 그래프의 분산 수행에 참여하는 테스크들의 집합

sebble

#!/bin/bash

USER=${1:-sebble}

STARS=$(curl -sI https://api.github.com/users/$USER/starred?per_page=1|egrep '^Link'|egrep -o 'page=[0-9]+'|tail -1|cut -c6-)
PAGES=$((658/100+1))

echo You have $STARS starred repositories.
echo

deanlyoung

Note

Apple will reject apps that are using private url schemes (Ugh, Apple....) if they are pretty much obvius. Some apps are rejected and others are not, so, be aware of this issue before implementing any of those URL's in your app as a feature.

Updates

• [UPDATE 4] iOS 10 update: apparently settings now can be reached using App-Pref instead of prefs
• [UPDATE 3] For now you just can use url schemes to open your apps's settings with Swift 3.0 (Xcode 8). I'll keep you informed when OS preferences can be reached
• [UPDATE 2] The openURL() method of UIApplication is now deprecated. You should use application(_:open:options:) instead
• [UPDATE 1] Not yet tested in iOS 10. It will fail because of policies changes in URL scheme handling.

j-min

# http://pytorch.org/tutorials/beginner/transfer_learning_tutorial.html

def exp_lr_scheduler(optimizer, epoch, init_lr=0.001, lr_decay_epoch=7):
    """Decay learning rate by a factor of 0.1 every lr_decay_epoch epochs."""
    lr = init_lr * (0.1**(epoch // lr_decay_epoch))

    if epoch % lr_decay_epoch == 0:
        print('LR is set to {}'.format(lr))

    for param_group in optimizer.param_groups:

ksseono

NAVER DEVIEW 2017 Slides

• 키노트 영상

DAY 1

• Open, Share, Enjoy : 네이버의 오픈소스 활동 (영상)
• 책 읽어주는 딥러닝: 배우 유인나가 해리포터를 읽어준다면 (데모, 소스코드, 영상)
• Chromium Binding 기술을 활용하여 Node.js와 네이티브 모듈 우아하게 연동하기 (영상)

siwalikm

'use strict';

const crypto = require('crypto');
const ENC_KEY = "bf3c199c2470cb477d907b1e0917c17b"; // set random encryption key
const IV = "5183666c72eec9e4"; // set random initialisation vector
// ENC_KEY and IV can be generated as crypto.randomBytes(32).toString('hex');

const phrase = "who let the dogs out";

var encrypt = ((val) => {