Penulis: admin

DrivenData: Hakuna Ma-data: Identify Wildlife on the Serengeti with AI for Earth

Link: https://www.drivendata.org/competitions/59/camera-trap-serengeti/

Overview

Leverage millions of images of animals on the Serengeti to build a classifier that distinguishes between gazelles, lions, and more!

In this competition, participants will predict the presence and species of wildlife in new camera trap data from the Snapshot Serengeti project, which boasts over 6 million images.

Camera traps are motion-triggered systems for passively collecting animal behavior data with minimal disturbance to their natural tendencies. Camera traps are an invaluable tool in conservation research, but the sheer amount of data they generate presents a huge barrier to using them effectively. This is where AI can help!

There are two immediate challenges where efforts like this competition are needed:

  • Camera traps can’t automatically label the animals they observe, creating an immense (and sometimes prohibitive) burden on humans to determine where and what wildlife are present.
  • Even when automated animal tagging models are available, the models that do exist don’t generalize well across time and locations, severely limiting their usefulness with new data.

To address these opportunities, we’re challenging data scientists, researchers, and developers from around the world to build the best algorithms for wildlife detection.

The competition is designed with a few objectives in mind:

  • Innovation: Participants use state-of-the-art approaches in computer vision and AI and get live feedback on how well their solutions perform
  • Generalization: This competition is designed to reward the best generalizable solutions. The private test data used to determine the winners will come entirely from the latest, unreleased season of data from the Snapshot Serengeti project (season 11). For more information on the competition timeline and evaluation, see the problem description.
  • Execution: Models are trained locally and submitted to execute inference in the cloud – read on!
  • Openness: All prize-winning models are released under an open source license for anyone to use and learn from

This is a brand new kind of DrivenData challenge! Previous models trained for camera trap images have often failed to generalize well. In this competition, we want to reward the models that generalize best to new images, so you won’t interact directly with the test set.  Rather than submitting your predicted labels for a test set you have, you’ll package up everything needed to do inference and send it to us. We’ll execute that code on Azure in a Docker container that has access to the test set images. By leveraging Microsoft Azure’s cloud computing platform and Docker containers, we’re moving our competition infrastructure one step closer to translating participants’ innovation into impact.

We can’t wait to run what you come up with!

National Data Science Challenge

National Data Science Challenge: https://careers.shopee.co.id/ndsc/

The objectives of the National Data Science Challenge (NDSC) are to:

  • Bring the tech community closer through working together and knowledge sharing
  • Provide an environment for the development of creative new ideas in Data Science
  • Equip students and professionals with essential technical skills and expertise to prepare them for Industry 4.0

Through this competition, we hope to showcase the ubiquity and usefulness of data in getting insights, thus reinforcing Indonesia’s emphasis on driving the digital economy and the use of big data.

Collaborative Challenge: Detecting Drought from Space

Deep Learning for Climate Adaptation: Detecting Drought from Space

The challenge

The dataset contains about 100,000 satellite images of Northern Kenya in 10 frequency bands, collected by the International Livestock Research Institute. Local experts (pastoralists, or nomadic herders) manually labeled the forage quality at the corresponding geolocations—specifically, the number of cows from {0, 1, 2, 3+} that the location at the center of the satellite image can feed. Each satellite image is 1.95km across, and each pixel in it represents a 30 meter square. Pastoralists estimate the forage quality within 20 meters when they stand on location, an area slightly larger than a pixel in the full 65×65-pixel satellite image. The satellite images thus provide a lot of extra context, which may prove useful since forage quality is correlated across space. The challenge is to learn a mapping from a satellite image to forage quality so we can more accurately predict drought conditions. Furthermore, the current labeling is very sparse, and we want dense predictions of forage quality at any pixel in a satellite image, not just at the center.

Buku Gratis Data Mining

Berikut ini beberapa buku data mining yang nampaknya bagus (dari situs http://christonard.com/12-free-data-mining-books/):

  1. An Introduction to Statistical Learning with Applications in R by James, Witten, Hastie & Tibshirani – . 426 Pages.
  2. The Elements of Statistical Learning by Hastie, Tibshirani & Friedman – 745 Pages.
  3. A Programmer’s Guide to Data Mining by Ron Zacharski –
  4. Probabilistic Programming & Bayesian Methods for Hackers by Cam Davidson-Pilson –
  5. Think Bayes, Bayesian Statistics Made Simple by Allen B. Downey –. 195 Pages.
  6. Data Mining and Analysis, Fundamental Concepts and Algorithms by Zaki & Meira –  599 Pages.
  7. An Introduction to Data Science by Jeffrey Stanton –  195 Pages.
  8. Machine Learning by Chebira, Mellouk & others –  422 Pages.
  9. Machine Learning – The Complete Guide –
  10. Bayesian Reasoning and Machine Learning by David Barber – 648 Pages.
  11. A Course in Machine Learning by Hal Daumé III – . 189 Pages.
  12. Information Theory, Inference and Learning Algorithms by David J.C. MacKay – 628 Pages.
  13. Modeling with Data by Ben Klemens –  454 Pages.
  14. Mining of Massive Datasets by Rajaraman & Ullman . 493 Pages

Instalasi Redmine 3.4.4-stable di Ubuntu 18.04.03

At the moment of writing this article, default installation in Ubuntu 18.04.03 will give you Redmine version 3.4.4.-stable

Installing Redmine 3.4.4-stable in 18.04.03
Use live server ISO (ubuntu-18.04.3-live-server-amd64.iso)

# reference: How to Install Redmine on Ubuntu step by stepapt-get update
apt-get upgrade

# install dependencies
apt install apache2 software-properties-common ruby-rmagick mysql-server mysql-client mysql-common ruby-dev build-essential libmysqlclient-dev libssl-dev gcc libmysqlclient-dev libapache2-mod-passenger libmagickcore-dev
apt install imagemagick-6.q16
apt-get install redmine redmine-mysql

# there may be questions from installer. Refer to Howto Install Redmine on Ubuntu www.redmine.org/projects/redmine/wiki/howto_install_redmine_on_ubuntu_step_by_step for explanation

# Next step is to upgrade all gems. It will take sometime to update all gems.

gem update

# possible error: connection problem.
# example erro message: Updating roadie
ERROR: Error installing roadie:
Unable to resolve dependency: user requested ‘roadie (= 3.5.0)’

gem install bundler

vi /etc/apache2/mods-available/passenger.conf

existing file:

<IfModule mod_passenger.c>
PassengerRoot /usr/lib/ruby/vendor_ruby/phusion_passenger/locations.ini
PassengerDefaultRuby /usr/bin/ruby
</IfModule>

Create symlink:

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

edit as follows:

<IfModule mod_passenger.c>
PassengerDefaultUser www-data
PassengerRoot /usr/lib/ruby/vendor_ruby/phusion_passenger/locations.ini
PassengerDefaultRuby /usr/bin/ruby
</IfModule>

edit file:

vi /etc/apache2/sites-available/000-default.conf

add the following lines:

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

Create Gemlock file:

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

service apache2 restart

browse to your website:

http://192.168.0.205/redmine/

with username: admin,
password: admin

You can check Redmine information in by following the menu : [Administration] -> [Information]

It will show something like this:

Default administrator account changed
Attachments directory writable
Plugin assets directory writable (./public/plugin_assets)
RMagick available (optional)
ImageMagick convert available (optional)

Environment:
Redmine version 3.4.4.stable
Ruby version 2.5.1-p57 (2018-03-29) [x86_64-linux-gnu]
Rails version 4.2.10
Environment production
Database adapter Mysql2
SCM:
Git 2.17.1
Filesystem
Redmine plugins:
no plugin installed

 

Redmine 3.4.4-stable

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