Meta tags:
description=sharing ideas, experiences, and randomness;

Headings (most frequently used words):

share, this, and, mine, categories, it, telkom, menulis, dan, bercerita, trial, fashion, mnist, dengan, cnn, starbase, get, funded, by, issuing, selling, tokens, fenomena, 411, posts, navigation, sharing, ideas, experiences, randomness,

Text of the page (most frequently used words):
x_train (16), model (15), x_test (15), keras (12), #fashion (12), 2013 (12), 2014 (12), 2015 (12), november (11), 2016 (11), mnist (11), dan (10), yang (10), data (10), 2012 (10), share (9), june (9), import (9), com (8), new (8), starbase (8), shape (8), add (8), ubyte (8), and (7), y_test (7), img_rows (7), img_cols (7), march (7), this (6), opens (6), window (6), facebook (6), may (6), blockchain (6), from (6), 2017 (6), y_train (6), print (6), january (6), april (6), july (6), with (5), website (5), menulis (5), bercerita (5), orang (5), open (5), saya (5), test (5), train (5), gzip (5), idx2numpy (5), 2009 (5), february (5), august (5), december (5), september (5), october (5), like (4), wordpress (4), comment (4), loading (4), projects (4), which (4), num_classes (4), reshape (4), input_shape (4), activation (4), dataset (4), images (4), idx3 (4), convert_from_string (4), read (4), labels (4), idx1 (4), t10k (4), http (4), central (4), amazonaws (4), dengan (4), ini (4), 2010 (4), itu (3), untuk (3), leave (3), thomhertsiadari (3), are (3), who (3), core (3), team (3), tokens (3), non (3), token (3), the (3), for (3), platform (3), sharing (3), simulasi (3), loss (3), accuracy (3), input (3), dense (3), dropout (3), conv2d (3), backend (3), batch_size (3), epochs (3), samples (3), cnn (3), relu (3), score (3), computer (3), vision (3), skip (3), zalando (3), 2011 (3), get (2), site (2), name (2), required (2), content (2), log (2), sign (2), subscribed (2), subscribe (2), blog (2), posts (2), sungguh (2), qur (2), benar (2), mereka (2), kafir (2), tipu (2), daya (2), karena (2), berilah (2), support (2), they (2), engineers (2), designers (2), marketers (2), providing (2), some (2), term (2), value (2), crowdfunding (2), pakai (2), load (2), load_data (2), sequential (2), layers (2), flatten (2), maxpooling2d (2), 128 (2), astype (2), float32 (2), 255 (2), class (2), utils (2), to_categorical (2), verbose (2), setelah (2), baru (2), pattern (2), recognition (2), ketika (2), group (2), hal (2), dari (2), juga (2), ideas (2), experiences (2), randomness (2), risna (2), mbak (2), life (2), started, design, email, write, comments, collapse, bar, manage, subscriptions, view, reader, report, privacy, already, have, account, now, join, other, subscribers, older, navigation, tariq, demi, langit, mengandung, hujan, bumi, mempunyai, tumbuh, tumbuhan, firman, pemisah, antara, hak, batil, bukanlah, sendagurauan, merencanakan, jahat, aku, pun, membuat, rencana, jitu, penangguhan, kepada, kesempatan, sementara, waktu, fenomena, 411, supporter, supporters, those, want, purchasing, working, etc, people, going, provide, currently, service, product, can, global, innovative, based, startups, business, planners, big, companies, artists, athletes, talents, event, organizer, frequently, used, industry, has, star, currency, symbol, mission, make, easy, everyone, start, aim, create, services, products, provides, crowdsourcing, recruiting, gives, long, incentive, mechanism, internet, what, both, closed, source, project, inc, will, technical, consulting, sourcing, enables, you, issue, conditional, templates, important, information, about, funded, issuing, selling, that, mudah, kan, selamat, mencoba, next, coba, sequence, rnn, hasil, atas, 23328696813583374, 91510000000000002, library, numpy, matplotlib, pyplot, models, parameters, image, dimensions, options, image_data_format, channels_first, else, normalization, convert, vectors, binary, matricess, build, simple, kernel_size, pool_size, softmax, summary, compile, losses, categorical_crossentropy, optimizer, optimizers, adadelta, metrics, fit, validation_data, evaluate, membangun, architecture, link, mengunduh, didownload, simpan, folder, kasus, def, return, berikut, sederhana, menggunaka, tensor, flow, sedikit, informasi, karakteristiknya, sama, luar, biasa, terkenal, belajar, pasti, pertama, kali, jadi, aja, penjelasan, panjangnya, bergabung, inapr, nya, indonesia, tertarik, bidang, menemukan, salah, satunya, adalah, sebuah, perusahaan, jerman, ikut, serta, iccv, venice, bulan, lalu, hadir, workshop, diselenggarakan, oleh, tau, sengaja, pergi, booth, pengen, kaos, gratis, maklum, mahasiswa, deep, learning, trial, sidebar, semangka, hangat, rahmawati, reza, dynasti, pramana, nurul, huda, uun, mas, ulik, thoifur, ato, pipin, ita, ratnasari, dedi, setiawan, bijak, fajar, asri, anggraini, aldo, wilman, telkom, workplace, tutorial, travel, note, technoship, startup, 166, sesi, curhat, ringkasan, buku, words, gak, jelas, pisang, ijo, series, others, nikah, islam, 168, korea, tugas, akhir, phd, master, degree, kuliah, kopikami, japan, healthy, side, events, delusional, categories, 2008, mine, menu,

Text of the page (random words):
menulis dan bercerita sharing ideas experiences and randomness skip to content skip to menu mine november 2017 1 june 2017 1 november 2016 1 october 2016 1 september 2016 2 august 2016 3 july 2016 3 june 2016 1 may 2016 2 march 2016 2 february 2016 4 january 2016 4 december 2015 3 november 2015 4 october 2015 4 september 2015 5 august 2015 16 july 2015 25 june 2015 22 may 2015 15 april 2015 8 march 2015 5 february 2015 1 january 2015 8 december 2014 4 november 2014 9 october 2014 6 september 2014 9 august 2014 8 july 2014 5 june 2014 11 may 2014 13 april 2014 6 march 2014 14 february 2014 6 january 2014 4 december 2013 3 november 2013 7 october 2013 11 september 2013 3 august 2013 3 july 2013 7 june 2013 8 may 2013 6 april 2013 2 march 2013 3 february 2013 2 january 2013 2 december 2012 6 november 2012 4 october 2012 5 september 2012 1 july 2012 11 june 2012 4 may 2012 3 april 2012 3 march 2012 3 january 2012 5 december 2011 2 november 2011 3 june 2011 1 august 2010 1 july 2010 2 april 2010 6 march 2010 4 june 2009 1 april 2009 14 march 2009 3 february 2009 5 january 2009 1 november 2008 7 categories delusional 11 events 20 healthy side 2 japan 1 kopikami 2 kuliah 41 master degree 10 phd life 23 tugas akhir 2 life in korea 168 my islam 54 nikah 1 others 45 pisang ijo series 166 gak jelas bo 31 my words 96 ringkasan buku 5 sesi curhat 48 startup 8 technoship 32 travel note 4 tutorial 3 workplace 22 it telkom aldo wilman asri anggraini bijak fajar p dedi setiawan ita ratnasari m thoifur ato pipin mas ulik nurul huda mbak uun reza dynasti pramana risna rahmawati mbak risna semangka hangat sidebar menulis dan bercerita sharing ideas experiences and randomness trial 1 fashion mnist dengan cnn november 11 2017 november 11 2017 thomhertsiadari computer vision deep learning fashion keras mnist leave a comment setelah bergabung dengan group wa inapr group nya orang indonesia yang tertarik bidang pattern recognition saya menemukan hal hal baru salah satunya adalah dataset fashion mnist dari zalando sebuah perusahaan fashion dari jerman ketika ikut serta iccv 2017 di venice bulan lalu saya juga hadir di workshop computer vision for fashion yang diselenggarakan oleh zalando ini tau zalando ini ga sengaja juga pergi ke booth mereka karena pengen kaos gratis maklum mahasiswa sedikit informasi fashion mnist ini karakteristiknya sama dengan mnist dataset yang luar biasa terkenal orang yang baru belajar pattern recognition dan computer vision pasti pakai dataset ini ketika pertama kali simulasi jadi saya skip aja penjelasan panjangnya berikut simulasi sederhana fashion mnist dengan cnn menggunaka keras backend tensor flow load data fashion mnist link untuk mengunduh data http fashion mnist s3 website eu central 1 amazonaws com train images idx3 ubyte gz http fashion mnist s3 website eu central 1 amazonaws com train labels idx1 ubyte gz http fashion mnist s3 website eu central 1 amazonaws com t10k images idx3 ubyte gz http fashion mnist s3 website eu central 1 amazonaws com t10k labels idx1 ubyte setelah didownload simpan dataset di folder data untuk kasus saya import gzip import idx2numpy def load_data with gzip open data train images idx3 ubyte gz rb as f x_train idx2numpy convert_from_string f read with gzip open data train labels idx1 ubyte gz rb as f y_train idx2numpy convert_from_string f read with gzip open data t10k images idx3 ubyte gz rb as f x_test idx2numpy convert_from_string f read with gzip open data t10k labels idx1 ubyte gz rb as f y_test idx2numpy convert_from_string f read return x_train y_train x_test y_test membangun architecture load data x_train y_train x_test y_test load_data input keras library import keras import numpy from matplotlib import pyplot from keras models import sequential from keras layers import dense flatten dropout from keras layers import conv2d maxpooling2d from keras import backend as k parameters batch_size 128 num_classes 10 epochs 12 input image dimensions img_rows img_cols 28 28 backend options if k image_data_format channels_first x_train x_train reshape x_train shape 0 1 img_rows img_cols x_test x_test reshape x_test shape 0 1 img_rows img_cols input_shape 1 img_rows img_cols else x_train x_train reshape x_train shape 0 img_rows img_cols 1 x_test x_test reshape x_test shape 0 img_rows img_cols 1 input_shape img_rows img_cols 1 data normalization x_train x_train astype float32 x_test x_test astype float32 x_train 255 x_test 255 print input samples print x_train shape x_train shape print x_train shape 0 train samples print x_test shape 0 test samples convert class vectors to binary class matricess y_train keras utils to_categorical y_train num_classes y_test keras utils to_categorical y_test num_classes build simple cnn model model sequential model add conv2d 32 kernel_size 3 3 activation relu input_shape input_shape model add conv2d 64 3 3 activation relu model add maxpooling2d pool_size 2 2 model add dropout 0 25 model add flatten model add dense 128 activation relu model add dropout 0 5 model add dense num_classes activation softmax model summary model compile loss keras losses categorical_crossentropy optimizer keras optimizers adadelta metrics accuracy model fit x_train y_train batch_size batch_size epochs epochs verbose 1 validation_data x_test y_test score model evaluate x_test y_test verbose 0 print test loss score 0 print test accuracy score 1 hasil simulasi di atas test loss 0 23328696813583374 test accuracy 0 91510000000000002 that s it mudah kan selamat mencoba next saya coba pakai sequence model rnn share this share on facebook opens in new window facebook share on x opens in new window x like loading starbase get funded by issuing and selling tokens june 12 2017 thomhertsiadari leave a comment important information about starbase what is starbase the platform name starbase is both an open and closed source project starbase inc will do technical consulting by providing a crowdfunding sourcing platform which enables you to issue conditional tokens from templates starbase s mission is to make it easy for everyone to start or support projects which aim to create new services and products starbase provides a crowdfunding and crowdsourcing recruiting platform which gives long term incentive sharing mechanism on the internet of value star currency symbol of starbase token token token is a frequently used term in the blockchain industry for data which has some value core team people who are going to provide or who are currently providing some service or product they can be global and innovative non blockchain based projects startups new business planners in big companies artists athletes talents event organizer supporter supporters are those who want to support projects by purchasing core team s tokens or by working on core team s projects they may be blockchain engineers designers non blockchain engineers designers blockchain marketers non blockchain marketers etc share this share on facebook opens in new window facebook share on x opens in new window x like loading fenomena 411 november 6 2016 thomhertsiadari leave a comment at tariq 11 17 11 demi langit yang mengandung hujan 12 dan bumi yang mempunyai tumbuh tumbuhan 13 sungguh al qur an itu benar benar firman pemisah antara yang hak dan yang batil 14 dan al qur an itu bukanlah sendagurauan 15 sungguh mereka orang kafir merencanakan tipu daya yang jahat 16 dan aku pun membuat rencana tipu daya yang jitu 17 karena itu berilah penangguhan kepada orang orang kafir berilah kesempatan untuk sementara waktu share this share on facebook opens in new window facebook share on x opens in new window x like loading posts navigation older posts blog at wordpress com menulis dan bercerita blog at wordpress com subscribe subscribed menulis dan bercerita join 63 other subscribers sign me up already have a wordpress com account log in now privacy menulis dan bercerita subscribe subscribed sign up log in report this content view site in reader manage subscriptions collapse this bar loading comments write a comment email required name required website d design a site like this with wordpress com get started