[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Implementation of Universal Transformer in Pytorch

Understanding the Difficulty of Training Transformers

Transformer-based image captioning extension for pytorch/fairseq

Based on the Pytorch-Transformers library by HuggingFace. To be used as a starting point for employing Transformer models in text classification tasks. Contains code to easily train BERT, XLNet, Ro…

Convai2 submission.

Inverse Compositional Spatial Transformer Networks 🎭 (CVPR 2017 oral)

ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing 👓 (CVPR 2018)

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

Transformer based on a variant of attention that is linear complexity in respect to sequence length

A Abstractive Summarization Implementation with Transformer and Pointer-generator

Meshed-Memory Transformer for Image Captioning. CVPR 2020

Code for the Convolutional Vision Transformer (ConViT)

A collection of resources to study Transformers in depth.

Code for "Text Generation from Knowledge Graphs with Graph Transformers"

[ACL'19] [PyTorch] Multimodal Transformer

PoolFormer: MetaFormer Is Actually What You Need for Vision (CVPR 2022 Oral)

A Visual Analysis Tool to Explore Learned Representations in Transformers Models

Official Pytorch implementation of "OmniNet: A unified architecture for multi-modal multi-task learning" | Authors: Subhojeet Pramanik, Priyanka Agrawal, Aman Hussain

Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

This is an official implementation for "Video Swin Transformers".

Graph Transformer Networks (Authors' PyTorch implementation for the NeurIPS 19 paper)

Transformer training code for sequential tasks

Recent Transformer-based CV and related works.

A Unified Library for Parameter-Efficient and Modular Transfer Learning

Graphormer is a general-purpose deep learning backbone for molecular modeling.

PyTorch code for EMNLP 2019 paper "LXMERT: Learning Cross-Modality Encoder Representations from Transformers".

[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

list of efficient attention modules

Pytorch library for fast transformer implementations