Posts | Catalyst

SearchCatalyst CatalystTl;drDocumentationCoursePostsTalksProjectsContactSlackLight Dark AutomaticPostsGSoC 2022 callList of Suggested Projects for GSoC 2022.Last updated on 09 Feb 2022 4 min readClassification in the wildA few best practices for machine learning classification tasks.Last updated on 09 Feb 2022 0 min readCatalyst.Neuro: A 3D Brain Segmentation Pipeline for MRICatalyst 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.Last updated on 24 Sep 2021 0 min readCatalyst — A PyTorch Framework for Accelerated Deep Learning R&DFor 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.Last updated on 24 Sep 2021 0 min readRepresentation Learning and FacesDuring 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.Last updated on 24 Sep 2021 0 min readCatalyst 102 — Core TrinityIn 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.Last updated on 24 Sep 2021 0 min readPruning with CatalystIn this post, I will continue the blog post series about reducing model size with an introduction to pruning neural networks.Last updated on 24 Sep 2021 0 min readMetric Learning with CatalystIn this post, I would like to tell you about a metric learning pipeline, which has been added in 20.08 release.Last updated on 24 Sep 2021 0 min readCatalyst dev blog - 20.07 releaseIn 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.Last updated on 24 Sep 2021 0 min readBERT Distillation with CatalystIn 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?Last updated on 24 Sep 2021 0 min read»Cite ×Copy Download