hsqmlzno1

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

faiss

A library for efficient similarity search and clustering of dense vectors.

Megatron-LM

Ongoing research training transformer models at scale

Awesome-Learning-with-Label-Noise

A curated list of resources for Learning with Noisy Labels

TransCoder

Public release of the TransCoder research project https://arxiv.org/pdf/2006.03511.pdf

mean-teacher

A state-of-the-art semi-supervised method for image recognition

tuixue.online-visa

https://tuixue.online/visa/ A Real-time Display of U.S. Visa Appointment Status Website 预约美帝签证各个签证处最早时间的爬虫

few-shot-meta-baseline

Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning, in ICCV 2021

tensor2robot

Distributed machine learning infrastructure for large-scale robotics research

DivideMix

Code for paper: DivideMix: Learning with Noisy Labels as Semi-supervised Learning

pseudo_label-pytorch

The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks

few_shot_gaze

Pytorch implementation and demo of FAZE: Few-Shot Adaptive Gaze Estimation (ICCV 2019, oral)

VAT-pytorch

Virtual Adversarial Training (VAT) implementation for PyTorch

vert-papers

This repository contains code and datasets related to entity/knowledge papers from the VERT (Versatile Entity Recognition & disambiguation Toolkit) project, by the Knowledge Computing group at Microsoft Research Asia (MSRA).

AttentionXML

Implementation for "AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification"

MetaLearning4NLP-Papers

A list of recent papers about Meta / few-shot learning methods applied in NLP areas.

moco.tensorflow

A TensorFlow re-implementation of Momentum Contrast (MoCo): https://arxiv.org/abs/1911.05722

weak-supervision-for-NER

Framework to learn Named Entity Recognition models without labelled data using weak supervision.

meta-learning-bert

Meta learning with BERT as a learner

l2b

Tensorflow implementation of "Learning to Balance: Bayesian Meta-learning for Imbalanced and Out-of-distribution Tasks" (ICLR 2020 oral)

LightXML

LightXML: Transformer with dynamic negative sampling for High-Performance Extreme Multi-label Text Classification

wiser

Framework for weakly supervised deep sequence taggers, focused on named entity recognition

daga

Data Augmentation with a Generation Approach for Low-resource Tagging Tasks

induction-network

复现论文《Few-Shot Text Classification with Induction Network》

pyMeta

Library to manage machine learning problems as `Tasks' and to sample from Task distributions. Includes Tensorflow implementation of implicit-MAML (iMAML), FOMAML and Reptile.

ECLARE

ECLARE: Extreme Classification with Label Graph Correlations

leopard

labelmodels

Lightweight implementations of generative label models for weakly supervised machine learning

MAML-Pytorch-Multi-GPUs

pytorch maml with Multi-GPUs, fast and simplest implementation

MetaNLP