A PyTorch Implementation of the Luna: Linear Unified Nested Attention

Overview

Unofficial PyTorch implementation of Luna: Linear Unified Nested Attention


The quadratic computational and memory complexities of the Transformer’s attention mechanism have limited its scalability for modeling long sequences. In this paper, we propose Luna, a linear unified nested attention mechanism that approximates softmax attention with two nested linear attention functions, yielding only linear (as opposed to quadratic) time and space complexity. As compared to a more traditional attention mechanism, Luna introduces an additional sequence with a fixed length as input and an additional corresponding output, which allows Luna to perform attention operation linearly, while also storing adequate contextual information. We perform extensive evaluations on three benchmarks of sequence modeling tasks: long-context sequence modeling, neural machine translation and masked language modeling for large-scale pretraining. Competitive or even better experimental results demonstrate both the effectiveness and efficiency of Luna compared to a variety of strong baseline methods including the full-rank attention and other efficient sparse and dense attention methods

image

Installation

This project recommends Python 3.7 or higher. We recommend creating a new virtual environment for this project (using virtual env or conda).

Prerequisites

  • Numpy: pip install numpy (Refer here for problem installing Numpy).
  • Pytorch: Refer to PyTorch website to install the version w.r.t. your environment.

Install from source

Currently we only support installation from source code using setuptools. Checkout the source code and run the following commands:

pip install -e .

Usage

import torch
from luna_transformer import LunaTransformerEncoder

DUMMY_INPUTS = torch.LongTensor([
    [2, 3, 3, 3, 3, 3, 2, 2, 0],
    [2, 3, 3, 3, 3, 3, 2, 3, 2],
    [2, 3, 3, 3, 3, 3, 2, 2, 0],
])
DUMMY_INPUT_LENGTHS = torch.LongTensor([9, 8, 7])

model = LunaTransformerEncoder(vocab_size=4, d_model=512, num_layers=6,
                               num_attention_heads=8, project_embedding_length=32,
                               dropout_p=0.1, max_length=1024)
ouputs = model(DUMMY_INPUTS, DUMMY_INPUT_LENGTHS)

Troubleshoots and Contributing

If you have any questions, bug reports, and feature requests, please open an issue on github or
contacts [email protected] please.

I appreciate any kind of feedback or contribution. Feel free to proceed with small issues like bug fixes, documentation improvement. For major contributions and new features, please discuss with the collaborators in corresponding issues.

Code Style

I follow PEP-8 for code style. Especially the style of docstrings is important to generate documentation.

Author

Owner
Soohwan Kim
Toward human-like A.I.
Soohwan Kim
Code for Parameter Prediction for Unseen Deep Architectures (NeurIPS 2021)

Parameter Prediction for Unseen Deep Architectures (NeurIPS 2021) authors: Boris Knyazev, Michal Drozdzal, Graham Taylor, Adriana Romero-Soriano Overv

Facebook Research 462 Jan 03, 2023
Re-implementation of 'Grokking: Generalization beyond overfitting on small algorithmic datasets'

Re-implementation of the paper 'Grokking: Generalization beyond overfitting on small algorithmic datasets' Paper Original paper can be found here Data

Tom Lieberum 38 Aug 09, 2022
We will release the code of "ConTNet: Why not use convolution and transformer at the same time?" in this repo

ConTNet Introduction ConTNet (Convlution-Tranformer Network) is proposed mainly in response to the following two issues: (1) ConvNets lack a large rec

93 Nov 08, 2022
Codebase for "ProtoAttend: Attention-Based Prototypical Learning."

Codebase for "ProtoAttend: Attention-Based Prototypical Learning." Authors: Sercan O. Arik and Tomas Pfister Paper: Sercan O. Arik and Tomas Pfister,

47 2 May 17, 2022
The code for our paper Semi-Supervised Learning with Multi-Head Co-Training

Semi-Supervised Learning with Multi-Head Co-Training (PyTorch) Abstract Co-training, extended from self-training, is one of the frameworks for semi-su

cmc 6 Dec 04, 2022
4st place solution for the PBVS 2022 Multi-modal Aerial View Object Classification Challenge - Track 1 (SAR) at PBVS2022

A Two-Stage Shake-Shake Network for Long-tailed Recognition of SAR Aerial View Objects 4st place solution for the PBVS 2022 Multi-modal Aerial View Ob

LinpengPan 5 Nov 09, 2022
Implementation for the IJCAI2021 work "Beyond the Spectrum: Detecting Deepfakes via Re-synthesis"

Beyond the Spectrum Implementation for the IJCAI2021 work "Beyond the Spectrum: Detecting Deepfakes via Re-synthesis" by Yang He, Ning Yu, Margret Keu

Yang He 27 Jan 07, 2023
Deep Learning as a Cloud API Service.

Deep API Deep Learning as Cloud APIs. This project provides pre-trained deep learning models as a cloud API service. A web interface is available as w

Wu Han 4 Jan 06, 2023
Re-implementation of the vector capsule with dynamic routing

VectorCapsule Re-implementation of the vector capsule with dynamic routing We implement the vector capsule and dynamic routing via graph neural networ

ZhenchaoTang 10 Feb 10, 2022
Eff video representation - Efficient video representation through neural fields

Neural Residual Flow Fields for Efficient Video Representations 1. Download MPI

41 Jan 06, 2023
HGCAE Pytorch implementation. CVPR2021 accepted.

Hyperbolic Graph Convolutional Auto-Encoders Accepted to CVPR2021 🎉 Official PyTorch code of Unsupervised Hyperbolic Representation Learning via Mess

Junho Cho 37 Nov 13, 2022
Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time

Semi Hand-Object Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time (CVPR 2021).

96 Dec 27, 2022
Prometheus exporter for Cisco Unified Computing System (UCS) Manager

prometheus-ucs-exporter Overview Use metrics from the UCS API to export relevant metrics to Prometheus This repository is a fork of Drew Stinnett's or

Marshall Wace 6 Nov 07, 2022
[BMVC'21] Official PyTorch Implementation of Grounded Situation Recognition with Transformers

Grounded Situation Recognition with Transformers Paper | Model Checkpoint This is the official PyTorch implementation of Grounded Situation Recognitio

Junhyeong Cho 18 Jul 19, 2022
[ICLR 2021 Spotlight Oral] "Undistillable: Making A Nasty Teacher That CANNOT teach students", Haoyu Ma, Tianlong Chen, Ting-Kuei Hu, Chenyu You, Xiaohui Xie, Zhangyang Wang

Undistillable: Making A Nasty Teacher That CANNOT teach students "Undistillable: Making A Nasty Teacher That CANNOT teach students" Haoyu Ma, Tianlong

VITA 71 Dec 28, 2022
Simultaneous Demand Prediction and Planning

Simultaneous Demand Prediction and Planning Dependencies Python packages: Pytorch, scikit-learn, Pandas, Numpy, PyYAML Data POI: data/poi Road network

Yizong Wang 1 Sep 01, 2022
Models, datasets and tools for Facial keypoints detection

Template for Data Science Project This repo aims to give a robust starting point to any Data Science related project. It contains readymade tools setu

girafe.ai 1 Feb 11, 2022
Playable Video Generation

Playable Video Generation Playable Video Generation Willi Menapace, Stéphane Lathuilière, Sergey Tulyakov, Aliaksandr Siarohin, Elisa Ricci Paper: ArX

Willi Menapace 136 Dec 31, 2022
(CVPR 2021) PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds by Mutian Xu*, Runyu Ding*, Hengshuang Zhao, and Xiaojuan Qi. Int

CVMI Lab 228 Dec 25, 2022
Keyhole Imaging: Non-Line-of-Sight Imaging and Tracking of Moving Objects Along a Single Optical Path

Keyhole Imaging Code & Dataset Code associated with the paper "Keyhole Imaging: Non-Line-of-Sight Imaging and Tracking of Moving Objects Along a Singl

Stanford Computational Imaging Lab 20 Feb 03, 2022