Albumentation – fast & flexible image augmentations

Image Augmentations is a powerful technique to improve model robustness and performance. There are many image augmentations libraries on the market: torchvision, imgaug, DALI, Augmentor, SOLT, etc.
In all of them, authors focussed on variety at the cost of speed, or the speed at the cost of flexibility.

Requirements for augmentations:
* Variety: they want to have a large set of standard and exotic augmentation for image classification, segmentation, and detection in one place.
* Performance: transforms should be as fast as possible.
* Flexibility: it should be easy to add new transforms or new types of transforms.
* Conciseness: all complexity of implementation should be hidden behind the API.

Albumentations were born out of necessity. The authors were actively participating in various Deep Learning competitions. To get to the top they needed something better than what was already available. All of them, independently, started working on more powerful augmentation pipelines. Later they merged their efforts and released the code in the form of the library.

To date Albumentations has more than 70 transforms and supports image classification, #segmentation, object and keypoint detection tasks.

The library was adopted by academics, Kaggle, and other communities.

ODS: #tool_albumentations
Link: https://albumentations.ai/
Github: https://github.com/albumentations-team/albumentations
Paper: https://www.mdpi.com/2078-2489/11/2/125

P.S. Following trend setup by #Catalyst team, we provide extensive description of project with the help of its creators.

#guestpost #augmentation #CV #DL #imageprocessing #ods #objectdetection #imageclassification #tool

ODS.ai in collaboration with Sberbank has launched a new competition to build an algorithm that most accurately predicts the dynamics of the number of reported cases of COVID-19 in each country over the next 7 days.

The objective of the competition is to draw attention to the forecasts of the coronavirus pandemic. Perhaps while solving this problem, you could find problems in the data sources or make a suitable forecast based on the most reliable data.

Remember, we are developing an open science in ODS.ai by creating new and testing the existing forecasting methods, so your input can help humanity to achieve bigger goals. Only solving the tasks based on the open and public benchmark we can test and compare different approaches, as well as come to the best practices, and make them accessible to the entire research community.


Link: https://ods.ai/competitions/sberbank-covid19-forecast

#ods #openscience #competition #sber

Open cool NOT Kaggle contest – AIJ Contest 2020 🎉

◼️ Digital Peter: Recognition of Peter the Great’s manuscripts
October 9 – November 8
Digital Peter is an educational task with a historical slant created on the basis of several AI technologies (CV, NLP, and knowledge graphs). The task was prepared jointly with the Saint Petersburg Institute of History of the Russian Academy of Sciences, Federal Archival Agency of Russia and the Russian State Archive of Ancient Acts.
Participants are invited to create an algorithm for line-by-line recognition of manuscripts written by Peter the Great.

◼️ NoFloodWithAI: Flash floods on the Amur river
October 9 – November 1
NoFloodWithAI is a special track with a socially important theme prepared jointly with the Ministry of Emergency Situations, Ministry of Natural Resources and Rosgidromet of Russia.
Participants are invited to develop an algorithm for short-term forecasting of water levels in the Amur River for the following settlements: Dzhalinda, Blagoveshchensk, Innokentievka, Leninskoye, Khabarovsk, Komsomolsk-on-Amur, Nikolaevsk-on-Amur for 10 days in advance in order to prevent emergency situations in Russia’s regions. The results of the contest will be reused to mitigate environmental risks and minimize economic damage wrought on the regions.


◼️ AI4Humanities: ruGPT-3
October 16 – November 1
It is a track developed especially for those familiar with artificial neural networks. It will help to learn about a promising ruGPT-3 technology able to generate very complex meaningful texts based on just one request made in natural human language. For example, it can help you answer most questions included in basic or unified national exams (OGE or EGE), write Java code at the request "Please make a website for the online shop", come up with a business idea for a new startup, or write new popular science articles.


more on the project page: https://ods.ai/tracks/aij2020

#ods #aij #contest #peter #floods #rugpt3