self-attention 开源项目推荐（519 个）

datawhalechina /leedl-tutorial

《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

zhouhaoyi /Informer2020

The GitHub repository for the paper "Informer" accepted by AAAI 2021.

cmhungsteve /Awesome-Transformer-Attention

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

PetarV- /GAT

Graph Attention Networks (https://arxiv.org/abs/1710.10903)

diegoantognini /pyGAT

Pytorch implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)

gordicaleksa /pytorch-GAT

My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!

github /CodeSearchNet

Datasets, tools, and benchmarks for representation learning of code.

microsoft /DeBERTa

The implementation of DeBERTa

NVlabs /MambaVision

[CVPR 2025] MambaVision的PyTorch官方实施：Mamba-Transformer混合视觉主干

speedinghzl /CCNet

CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).

DirtyHarryLYL /Transformer-in-Vision

Recent Transformer-based CV and related works.

The-AI-Summer /self-attention-cv

Implementation of various self-attention mechanisms focused on computer vision. Ongoing repository.

Separius /awesome-fast-attention

list of efficient attention modules

brightmart /bert_language_understanding

面向语言理解的深度双向 Transformer 预训练：预训练 TextCNN

NVlabs /FasterViT

[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention

xxxnell /how-do-vits-work

(ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"

prakashpandey9 /Text-Classification-Pytorch

Text classification using deep learning models in Pytorch

kaituoxu /Speech-Transformer

A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.

daiquocnguyen /Graph-Transformer

Universal Graph Transformer Self-Attention Networks (TheWebConf WWW 2022) (Pytorch and Tensorflow)

chsiang426 /ML-2021-notes

臺灣大學 (NTU) 李宏毅教授「機器學習 (Machine Learning) 2021 Spring 」課程筆記