alno

imgaug

Image augmentation for machine learning experiments.

candle

Minimalist ML framework for Rust

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

tensorboardX

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

obsidian-dataview

A data index and query language over Markdown files, for https://obsidian.md/.

Practical_RL

A course in reinforcement learning in the wild

YaLM-100B

Pretrained language model with 100B parameters

eli5

A library for debugging/inspecting machine learning classifiers and explaining their predictions

userver

Production-ready C++ Asynchronous Framework with rich functionality

obsidian-tasks

Task management for the Obsidian knowledge base.

divkit

DivKit is an open source Server-Driven UI (SDUI) framework. SDUI is a an emerging technique that leverage the server to build the user interfaces of their mobile app

Practical_DL

DL course co-developed by YSDA, HSE and Skoltech

StackNet

StackNet is a computational, scalable and analytical Meta modelling framework

sparsepp

A fast, memory efficient hash map for C++

datalens

A modern, scalable analytics system

bpemb

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

obsidian-dataloom

Weave together data from diverse sources and display them in different views. Inspired by Excel spreadsheets and Notion.so.

text2vec

Fast vectorization, topic modeling, distances and GloVe word embeddings in R.

tffm

TensorFlow implementation of an arbitrary order Factorization Machine

heamy

A set of useful tools for competitive data science.

Wordbatch

Python library for distributed AI processing pipelines, using swappable scheduler backends.

momoko

Wraps (asynchronous) Psycopg2 for Tornado.

vision_networks

Repo about neural networks for images handling

ultrasound-nerve-segmentation

Kaggle Ultrasound Nerve Segmentation competition [Keras]

awesome-ml

Machine Learning Awesome List

TickTickSync

Coda

Samsung Natural Language Processing Pipeline (basically for Russian language): morphology, dependency parser and much more

batch-learn

FTRL

R/Rcpp implementation of the 'Follow-the-Regularized-Leader' algorithm

kaggle-lions-2017

2nd place solution for Kaggle NOAA Fisheries Steller Sea Lion Population Count