A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilizatio…

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

Fast and memory-efficient exact attention

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it

Noah Research

TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models

A collection of AWESOME things about domain adaptation

Code Release for "Learning to Detect Open Classes for Universal Domain Adaptation"(ECCV2020)

NeurIPS'19: Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting (Pytorch implementation for noisy labels).

TensorFlow and PyTorch implementations of "Meta-Transfer Learning for Few-Shot Learning" (CVPR2019)

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch

Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)

ICCV2019最新录用情况

A curated list of awesome self-supervised methods

All about domain generalization

Code for Semi-Supervised Learning by Augmented Distribution Alignment

A curated list of Meta Learning papers, code, books, blogs, videos, datasets and other resources.

Repository for few-shot learning machine learning projects

The demo code for the MLDG paper "Learning to Generalize: Meta-Learning for Domain Generalization", https://arxiv.org/abs/1710.03463, https://arxiv.org/pdf/1710.03463.pdf

Zero-Shot Learning with GCN (CVPR 2018)

Meta Learning / Learning to Learn / One Shot Learning / Few Shot Learning

Code for 'Open Set Domain Adaptation by Backpropagation'

An unofficial pytorch implementation of algorithms for domain adaptation

Pytorch implementation of Self-Attention Generative Adversarial Networks (SAGAN)

Siamese and triplet networks with online pair/triplet mining in PyTorch

Caffe models (includimg classification, detection and segmentation) and deploy files for famouse networks