Posts

List of Suggested Projects for GSoC 2022.

A few best practices for machine learning classification tasks.

Catalyst and TReNDS have been working together on applications of deep learning for neuroimaging and brain dynamics. This post describes the fundamental concepts implemented in Catalyst.Neuro and introduces different deep learning models comparison on brain segmentation task.

For the last three years, Catalyst-Team has been working on Catalyst — a high-level PyTorch framework for Deep Learning Research and Development. In this post, I would like to share our vision on high-level Deep Learning framework API and show current development progress on various examples.

During the last two years, there was enormous progress in representation learning through the Face Recognition task. Starting from well-known ArcFace in 2018, there were a few other “Faces”: SubCenterArcFace, CosFace, AdaCos, CurricularFace, and more. In this post, we would dive into “Faces”, introduce their intuition, and compare them on a small toy task.

In this tutorial, I would like to go through our first deep learning course homework and introduce your 3 Catalyst main abstractions — Experiment, Runner, and Callback.

In this post, I will continue the blog post series about reducing model size with an introduction to pruning neural networks.

In this post, I would like to tell you about a metric learning pipeline, which has been added in 20.08 release.

In this post, I would like to share with you our development progress for the last month. Let’s check what features we have added to the framework in such a short time.

In the last few years, NLP models have made a big leap in most machine learning tasks. BERT or BERT-based models are the most popular NLP models currently. But there is one big problem - there are about 110 million parameters which could decrease inference speed. Could we get our model smaller without losing quality?