494 Open source projects that are alternatives of or similar to libai

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

SOTA Semantic Segmentation Models in PyTorch

[MICCAI2022] This is an official PyTorch implementation for A Robust Volumetric Transformer for Accurate 3D Tumor Segmentation

Implementation of autoregressive language model using improved Transformer and DeepSpeed pipeline parallelism.

TransMorph: Transformer for Unsupervised Medical Image Registration (PyTorch)

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

(ICCV 2021) BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search

SwinIR: Image Restoration Using Swin Transformer (official repository)

pix2tex: Using a ViT to convert images of equations into LaTeX code.

Official PyTorch Implementation of Long-Short Transformer (NeurIPS 2021).

A collection of SOTA Image Classification Models in PyTorch

The Tensorflow, Keras implementation of Swin-Transformer and Swin-UNET

PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，BEiT，MAE等图像自监督算法以及 Vision Transformer，DEiT，Swin Transformer，CvT，T2T-ViT，MLP-Mixer，XCiT，ConvNeXt，PVTv2 等基础视觉算法

Paddle Large Scale Classification Tools，supports ArcFace, CosFace, PartialFC, Data Parallel + Model Parallel. Model includes ResNet, ViT, DeiT, FaceViT.

a collection of visualization function

You Only Look at One Sequence (NeurIPS 2021)

One Person, One Model, One World: Learning Continual User Representation without Forgetting

CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.

Sequence to Sequence Models in PyTorch

Codes to pre-train Japanese T5 models

Build English-Vietnamese machine translation with ProtonX Transformer. :D

This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".

⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.

Implementation of Conv-based and Vit-based networks designed for CIFAR.

[ICRA 2020] Train generalizable policies for kit assembly with self-supervised dense correspondence learning.

Codes and Datasets for paper RecSys'20 "SSE-PT: Sequential Recommendation Via Personalized Transformer" and NurIPS'19 "Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers"

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

Java 字节操作的工具库(不是字节码的工具库)

A curated list of awesome resources combining Transformers with Neural Architecture Search

Generate images from texts. In Russian

[CVPR 2020] Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation (PyTorch)

Object-aware Contrastive Learning for Debiased Scene Representation (NeurIPS 2021)

Nested Hierarchical Transformer https://arxiv.org/pdf/2105.12723.pdf

Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations. [NeurIPS 2021]

official implemntation for "Contrastive Learning with Stronger Augmentations"

Video Representation Learning by Recognizing Temporal Transformations. In ECCV, 2020.

📄 Spatial Contrastive Learning for Few-Shot Classification (ECML/PKDD 2021).

PyTorch implementation of some learning rate schedulers for deep learning researcher.

[NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)

PyTorch solution of named entity recognition task Using Google AI's pre-trained BERT model.

Code for the paper "MASTER: Multi-Aspect Non-local Network for Scene Text Recognition" (Pattern Recognition 2021)

Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.

Repository for Project Insight: NLP as a Service

Create Horovod cluster easily using Ansible

Leetcode using AI

Transformer-based Memory Networks for Knowledge Graph Embeddings (ACL 2020) (Pytorch and Tensorflow)

TianChi AIEarth Contest Solution

Tool for visualizing attention in the Transformer model (BERT, GPT-2, Albert, XLNet, RoBERTa, CTRL, etc.)

An implementation of DeepMind's Relational Recurrent Neural Networks in PyTorch.

LONG-TERM SERIES FORECASTING WITH QUERYSELECTOR – EFFICIENT MODEL OF SPARSEATTENTION

Chinese NewsTitle Generation Project by GPT2.带有超级详细注释的中文GPT2新闻标题生成项目。

PostHTML is a tool to transform HTML/XML with JS plugins

Neural Relation Understanding: neural cardinality estimators for tabular data

A Robustly Optimized BERT Pretraining Approach for Vietnamese

Easy to use NLP library built on PyTorch and TorchText

2018-JDDC大赛第4名的解决方案

Dense video captioning in PyTorch

Meshed-Memory Transformer for Image Captioning. CVPR 2020

transformer, multi-graph transformer, graph, graph classification, sketch recognition, sketch classification, free-hand sketch, official code of the paper "Multi-Graph Transformer for Free-Hand Sketch Recognition"

Pinpoint Node.js agent