Instalasi Redmine 4.01 di Ubuntu 19.04

Prosedur instalasi Redmine di Ubuntu secara umum dapat dibaca di http://www.redmine.org/projects/redmine/wiki/howto_install_redmine_on_ubuntu_step_by_step , namun untuk setiap versi Ubuntu ada kemungkina perbedaan-perbedaan kecil.

Instalasi Aplikasi Pendukung

Berikut ini proses instalasi aplikasi pendukung Redmine:

apt-get update
apt-get remove cryptsetup-initramfs #optional, karena kadang-kadang kalau apt-get upgrade jadi macet di sini
apt-get upgrade
apt-get install apache2 software-properties-common ruby-rmagick mysql-server mysql-client mysql-common
apt-get install ruby-dev build-essential libmysqlclient-dev libssl-dev gcc libmysqlclient-dev
apt-get install libapache2-mod-passenger # untuk integrasi apache-passenger
 

apt-get install imagemagick libmagickcore-dev libmagickwand-dev
apt-get install libmagickcore-dev # untuk rmagick , menghindari pesan "ERROR: Can't install RMagick 4.0.0." https://stackoverflow.com/questions/28324439/cant-install-rmagick-0-0-0-cant-find-magick-config
 

apt-get install redmine redmine-mysql
gem update
gem install bundler
bundle update

Konfigurasi Apache

edit file /etc/apache2/mods-available/passenger.conf 

existing:

PassengerRoot /usr/lib/ruby/vendor_ruby/phusion_passenger/locations.ini PassengerDefaultRuby /usr/bin/ruby

ditambah “PassengerDefaultUser www-data” menjadi:

PassengerDefaultUser www-data
PassengerRoot /usr/lib/ruby/vendor_ruby/phusion_passenger/locations.ini PassengerDefaultRuby /usr/bin/ruby

tambahkan symlink:

ln -s /usr/share/redmine/public /var/www/html/redmine

edit file /etc/apache2/sites-available/000-default.conf , tambahkan sebagai berikut:

<Directory /var/www/html/redmine>
    RailsBaseURI /redmine
    PassengerResolveSymlinksInDocumentRoot on
</Directory>

Tambahkan file lock untuk Gemfile

touch /usr/share/redmine/Gemfile.lock
chown www-data:www-data /usr/share/redmine/Gemfile.lock

Restart Apache supaya konfigurasi dibaca ulang:

service apache2 restart

cek di browser:

ke alamat http://192.168.0.203/redmine

default username: admin, default password: admin
setelah login akan diminta untuk mengganti password

Pengecekan

Tampilan Administrator -> Information

Redmine 4.01 Information

 

LVIS Challenge 2019

Facebook has just introduced a great dataset and corresponding machine learning challenge at same time. The dataset is named LVIS (Large Vocabulary Instance Segmentation).

This is a great visual instance dataset.

Sample dataset

The challenge: https://www.lvisdataset.org/challenge

Today, rigorous evaluation of general purpose object detectors is mostly performed in the few category regime (e.g. 80) or when there are a large number of training examples per category (e.g. 100 to 1000+). LVIS provides an opportunity to enable research in the setting where there are a large number of categories and where per-category data is sometimes scarce.
Given that state-of-the-art deep learning methods for object detection perform poorly in the low-sample regime, we believe that our dataset poses an important and exciting new scientific challenge.

The dataset: https://www.lvisdataset.org/dataset

Source: https://twitter.com/facebookai/status/1159548405867139074

Making Indonesia 4.0

Kumpulan artikel-artikel tentang “Making Indonesia 4.0”.

Making Indonesia 4.0

Dokumen Resmi Making Indonesia 4.0

Artikel Berita tentang Making Indonesia 4.0

Machine Learning and Data Science Competition 2019

Object Detection State of The Art Progress

List of object detection progress:

  • R-CNN
  • Overfeat
  • Multibox
  • SPP-Net
  • MR-CNN
  • DeepBox
  • AttentionNet
  • Fast R-CNN
  • Deep[Proposal
  • Faster R-CNN
  • OHEM
  • YOLO v1
  • G-CNN
  • AZNet
  • Inside-OutsideNet (ION)
  • Hypernet
  • CRAFT
  • MultiPathNet (MPN)
  • SSD
  • GBDNet
  • CPF
  • MS-CNN
  • R-FCN
  • PVANET
  • DeepID
  • NoC
  • DSSD
  • TDM
  • YOLO v2
  • Feature Pyramid (FPN)
  • RON
  • DCN
  • DeNet
  • CoupleNet
  • RetinaNet
  • DSOD
  • Mask R-CNN
  • SMN
  • YOLO v3
  • SIN
  • STDN
  • RefineDet
  • MLKP
  • Relation-Net
  • Cascade R-CNN
  • RFBNet
  • CornetNet
  • Pelee
  • MethAnchor
  • SNIPER
  • M2Det

Reference: https://deeplearning.mit.edu/

Siaran Pers Bersama Terkait Bencana Selat Sunda

Berikut ini siaran pers bersama, yang nampaknya pengumuman resmi paling lengkap sejauh ini tentang bencana tsunami di Selat Sunda.

Siaran Pers Bersama dari lembaga-lembaga berikut:

  • Badan Informasi Geospasial (BIG) (https://twitter.com/InfoGeospasial)
  • Kementrian Koordinator Bidang Kemaritiman (https://twitter.com/kemaritiman)
  • Badan Pengkajian & Penerapan Teknologi (BPPT) (https://twitter.com/BPPT_RI)
  • BMKG (https://twitter.com/infoBMKG)
  • Lembaga Ilmu Pengetahuan Indonesia (LIPI) (https://twitter.com/lipiindonesia)
  • Badan Geologi
Halaman 1
Halaman 2
Lampiran 1
Lampiran

Sumber data ini adalah twitter dari BIG (Badan Informasi Geospasial) dalam format gambar JPG. Sejauh ini belum didapatkan versi PDF ataupun versi website.

Sumber:

Simple Image Classification with Keras

Keras logo

There are several kind of image classification:

  • Binary classification
  • Multiclass classification
  • Multi label classification

Image generation method for training

  • image.ImageGenerator.flow_from_directory()
  • image.ImageGenerator.flow()

Various models for training (built on model)

  • Xception
  • VGG16
  • VGG19
  • Resnet50
  • InceptionV3
  • InceptionResNetV2
  • MobileNet
  • DenseNet 
  • NASNet
  • MobileNetV2

Keras built in models usually have pre-trained weight on Imagenet, which significantly speeds up training, but those weights are only available for some image sizes.

There are two techniques to feed image files for prediction in Keras:

  • keras.preprocessing.image.flow_from_directory() 
  • keras.preprocessing.image.flow()

Simple Tutorials

Reference