An overview of approaches to communication used in distributed Deep Learning medium.com/@yaroslavvb/co…

Catalyst - 2 weeks summary - finetuning with all best practices (lrfinder, stages, grid search) and knn - segmentation with unet - Travis CI (tnx to @cclauss) - any pytorch scheduler support - global refactoring for state and callbacks (tnx to Artur Kuzin ) github.com/Scitator/catal…

MaskRCNN-Benchmark: - A fast, modular reference of {Mask,Faster}RCNN - by Francisco Massa (PyTorch), optimized by Nvidia - reusable components, pre-trained models - optimized inference, live demo Hope to see mmdetection and other great projects reuse the code! github.com/facebookresear…

Towards Catalyst 1.0 preview – all deprecated stuff removed – updated CI – refactored contrib – registry for models/losses/callbacks extensions and finally, fully refactored Catalyst.RL with new example github.com/scitator/catal… 🎉 Stay tuned!

New session of mlcourse.ai, open Machine Learning course by ods.ai @odsai_en takes off on Feb 11 and will be much more focused on competitions. If you'd like to quickly dive into the world of Kaggle, this course is for you bit.ly/2TWfC8d

После 18-го февраля начнется новая версия курса "Deep Learning на пальцах", на этот раз открытая для всех. Лекции, где можно задавать вопросы, задания на Питоне, тусовка в чатиках. Если вы все откладывали разобраться с deep learning - самое время! dlcourse.ai

mlcourse.ai is a 10-week course that starts tomorrow. It was created with input from a bunch of Kaggle Grandmasters. Starts with manipulating data using Pandas. covers feature engineering, time series forecasting and training using GBMs.

I would like to announce that @albuslaev creaf Одна інтеллектуальна одиниця Vladimir Iglovikov are releasing image augmentation library #albumentations v0.2.0. The new features are key point transformations, multiple targets of the same type and many other improvements. github.com/albu/albumenta…

We in Constanta just open sourced TensorStream: a library for fast and simple #GPU accelerated #DL models inference on video streams or files. It performs frames decoding and preprocessing with #nvidia #cuda and outputs #pytorch tensors right on a GPU. github.com/Fonbet/argus-t…

Glad to announce my new paper on #breastcancer Cellularity Assessment using #deeplearning! ArXiv preprint lnkd.in/ddQf6S2 Joint work with Viktor Alexandr Kalinin Alexey Shvets Vladimir Iglovikov Sergey Nikolenko #breastcancer #deep_learning #AI #machine_learning

Learn how to use the the Serverless Framework to deploy hybrid serverless/cluster workflows. This approach uses #aws Step Functions as the orchestrator between #lambda and #fargate serverless.com/blog/deploy_hy… by Rustem Feyzkhanov

🔥 Thrilled to release our Swift Core ML implementation of BERT for question answering.🔥🔥 Transformers models now also live on the edge. 📱📲 You now CAN do state-of-the-art NLP on mobile devices! github.com/huggingface/sw… Built w/ Lysandre and Thomas Wolf at Hugging Face

Pushed 3 new chapters to book "The Mechanics of Machine Learning" (by me and Jeremy Howard) mlbook.explained.ai These chaps detail EDA and model training for bulldozer sales Kaggle competition.

Glad to announce that our paper on #breastcancer Cellularity Assessment using #deeplearning has just been accepted for publication in the proceedings of #ICCV - #VRMI 2019 Joint work with Viktor Alexandr Kalinin Alexey Shvets Vladimir Iglovikov Sergey Nikolenko arxiv.org/abs/1905.01743

I'd like to share our work on applying deep learning to verify hydrocephalus on brain MRIs arxiv.org/abs/1909.10473 Thanks to Jeremy Howard and fastai for providing great DL framework and Alexey Shvets for help with preparing the paper and Overleaf tool explanations.

Minimal PyTorch implementation of YOLOv4 github.com/Tianxiaomo/pyt… #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch

Who on Earth is this?! 😍😍😍 Steven Brunton from WashingtonUniversity! me.washington.edu/facultyfinder/… This is absolutely nuts! 🤯🤩🥳 Laplace transform video: youtu.be/7UvtU75NXTg Check him out! The bar keeps rising! I'm in awe 😍 To infinity and beyond! 🚀

In this beginner tutorial, Alfredo and William walk through how to create a PyTorch classification model from scratch. It introduces all the fundamental components like architecture definition, optimizer, loss function, and more. youtube.com/watch?v=OMDn66…