304K subscribers
4.01K photos
710 videos
17 files
4.59K links
Погружаемся в машинное обучение и Data Science

Показываем как запускать любые LLm на пальцах.

По всем вопросам - @haarrp

@itchannels_telegram -🔥best channels

Реестр РКН: clck.ru/3Fmqri
Download Telegram
FreezeD: A Simple Baseline for Fine-tuning GANs
Simple Baseline for Fine-Tuning GANs

Code: https://github.com/sangwoomo/freezeD

Paper: https://arxiv.org/abs/2002.10964

Datasets: https://vcla.stat.ucla.edu/people/zhangzhang-si/HiT/exp5.html
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods

FlyingSquid is a new framework for automatically building models from multiple noisy label sources.

Code: https://github.com/HazyResearch/flyingsquid

Blog: https://hazyresearch.stanford.edu/flyingsquid

Paper: https://arxiv.org/abs/2002.11955v1
Meta-Transfer Learning for Zero-Shot Super-Resolution

Code: https://github.com/JWSoh/MZSR

Paper: https://arxiv.org/abs/2002.12213v1
This media is not supported in your browser
VIEW IN TELEGRAM
Deep Image Spatial Transformation for Person Image Generation
Pose-guided person image generation is to transform a source person image to a target pose.

Github: https://github.com/RenYurui/Global-Flow-Local-Attention

Paper: https://arxiv.org/abs/2003.00696v1
Sign Language Recognition with Deep Learning and PyTorch

https://theaisummer.com/Sign-Language-Recognition-with-PyTorch/
A software toolkit for research on general-purpose text understanding models

jiant is a software toolkit for natural language processing research, designed to facilitate work on multitask learning and transfer learning for sentence understanding tasks

https://jiant.info/

Code: https://github.com/nyu-mll/jiant

Paper: https://arxiv.org/pdf/2003.02249v1.pdf
Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation (PyTorch)

Code: https://github.com/cmhungsteve/SSTDA

Paper: https://arxiv.org/abs/2003.02824
🎇Announcing TensorFlow Quantum: An Open Source Library for Quantum Machine Learning

https://ai.googleblog.com/2020/03/announcing-tensorflow-quantum-open.html
Lagrangian Neural Networks

In contrast to Hamiltonian Neural Networks, these models do not require canonical coordinates and perform well in situations where generalized momentum is difficult to compute

Code: https://github.com/MilesCranmer/lagrangian_nns

Paper: https://arxiv.org/abs/2003.04630v1
On the Texture Bias for Few-Shot CNN Segmentation

This repository contains the code for deep auto-encoder-decoder network for few-shot semantic segmentation with state of the art results on FSS 1000 class dataset and Pascal 5i

Code: https://github.com/rezazad68/fewshot-segmentation

Paper: https://arxiv.org/abs/2003.04052v1

Download 1000-class dataset
This media is not supported in your browser
VIEW IN TELEGRAM
🌐 Fast and Easy Infinitely Wide Networks with Neural Tangents

Neural Tangents is a high-level neural network API for specifying complex, hierarchical, neural networks of both finite and infinite width. Neural Tangents allows researchers to define, train, and evaluate infinite networks as easily as finite ones.

https://ai.googleblog.com/2020/03/fast-and-easy-infinitely-wide-networks.html

Colab notebook: https://colab.research.google.com/github/google/neural-tangents/blob/master/notebooks/neural_tangents_cookbook.ipynb#scrollTo=Lt74vgCVNN2b

Code: https://github.com/google/neural-tangents

Paper: https://arxiv.org/abs/1912.02803