Code to reprudece NeurIPS paper: Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks

Overview

Accelerated Sparse Neural Training: A Provable and Efficient Method to FindN:M Transposable Masks

Recently, researchers proposed pruning deep neural network weights (DNNs) using an $N:M$ fine-grained block sparsity mask. In this mask, for each block of M weights, we have at least N zeros. In contrast to unstructured sparsity, N:M fine-grained block sparsity allows acceleration in actual modern hardware. Previously suggested solutions enabled DNN acceleration at the inference phase. To also allow such acceleration in the training phase, we suggest a novel transposable-fine-grained sparsity mask where the same mask can be used for both forward and backward passes. Our transposable mask ensures that both the weight matrix and its transpose follow the same sparsity pattern; thus the matrix multiplication required for passing the error backward can also be accelerated. We discuss the transposable constraint and devise a new measure for mask constraints, called mask-diversity (MD), which correlates with their expected accuracy. Lastly, we formulate the problem of finding the optimal transposable mask as a minimum-cost-flow problem and suggest a fast linear approximation that can be used when the masks dynamically change while training. Our experiments suggest 2x speed-up with no accuracy degradation over vision and language models. A reference implementation is available in the supplementary material.

Reproducing the results

This repository is partially based on convNet.pytorch repo. please ensure that you are using pytorch 1.7+. Reproducing AdaPrune results

cd AdaPrune
sh scripts/adaprune_dense_bnt.sh
sh scripts/adaprune_sparse.sh

Reproducing static NM-transposable starting from dense pre-trained model:

cd static_TNM
sh scripts/prune_pretrained_R50.sh

Reproducing dynamic NM-transposable from scratch:

cd dynamic_TNM
sh scripts/clone_and_copy.sh
sh scripts/run_R18.sh
sh scripts/run_R50.sh
Owner
itay hubara
itay hubara
Implementation of some unbalanced loss like focal_loss, dice_loss, DSC Loss, GHM Loss et.al

Implementation of some unbalanced loss for NLP task like focal_loss, dice_loss, DSC Loss, GHM Loss et.al Summary Here is a loss implementation reposit

121 Jan 01, 2023
中文空间语义理解评测

中文空间语义理解评测 最新消息 2021-04-10 🚩 排行榜发布: Leaderboard 2021-04-05 基线系统发布: SpaCE2021-Baseline 2021-04-05 开放数据提交: 提交结果 2021-04-01 开放报名: 我要报名 2021-04-01 数据集 pa

40 Jan 04, 2023
Constituency Tree Labeling Tool

Constituency Tree Labeling Tool The purpose of this package is to solve the constituency tree labeling problem. Look from the dataset labeled by NLTK,

张宇 6 Dec 20, 2022
PyTorch impelementations of BERT-based Spelling Error Correction Models.

PyTorch impelementations of BERT-based Spelling Error Correction Models

Heng Cai 209 Dec 30, 2022
GPT-3: Language Models are Few-Shot Learners

GPT-3: Language Models are Few-Shot Learners arXiv link Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-trainin

OpenAI 12.5k Jan 05, 2023
Autoregressive Entity Retrieval

The GENRE (Generative ENtity REtrieval) system as presented in Autoregressive Entity Retrieval implemented in pytorch. @inproceedings{decao2020autoreg

Meta Research 611 Dec 16, 2022
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

State-of-the-art Natural Language Processing for PyTorch and TensorFlow 2.0 🤗 Transformers provides thousands of pretrained models to perform tasks o

Hugging Face 77.3k Jan 03, 2023
使用pytorch+transformers复现了SimCSE论文中的有监督训练和无监督训练方法

SimCSE复现 项目描述 SimCSE是一种简单但是很巧妙的NLP对比学习方法,创新性地引入Dropout的方式,对样本添加噪声,从而达到对正样本增强的目的。 该框架的训练目的为:对于batch中的每个样本,拉近其与正样本之间的距离,拉远其与负样本之间的距离,使得模型能够在大规模无监督语料(也可以

58 Dec 20, 2022
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents

BROS (BERT Relying On Spatiality) is a pre-trained language model focusing on text and layout for better key information extraction from documents. Given the OCR results of the document image, which

Clova AI Research 94 Dec 30, 2022
Code for our paper "Mask-Align: Self-Supervised Neural Word Alignment" in ACL 2021

Mask-Align: Self-Supervised Neural Word Alignment This is the implementation of our work Mask-Align: Self-Supervised Neural Word Alignment. @inproceed

THUNLP-MT 46 Dec 15, 2022
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Hiring We are hiring at all levels (including FTE researchers and interns)! If you are interested in working with us on NLP and large-scale pre-traine

Microsoft 7.8k Jan 09, 2023
Python utility library for compositing PDF documents with reportlab.

pdfdoc-py Python utility library for compositing PDF documents with reportlab. Installation The pdfdoc-py package can be installed directly from the s

Michael Gale 1 Jan 06, 2022
Spokestack is a library that allows a user to easily incorporate a voice interface into any Python application with a focus on embedded systems.

Welcome to Spokestack Python! This library is intended for developing voice interfaces in Python. This can include anything from Raspberry Pi applicat

Spokestack 133 Sep 20, 2022
edge-SR: Super-Resolution For The Masses

edge-SR: Super Resolution For The Masses Citation Pablo Navarrete Michelini, Yunhua Lu and Xingqun Jiang. "edge-SR: Super-Resolution For The Masses",

Pablo 40 Nov 10, 2022
Tevatron is a simple and efficient toolkit for training and running dense retrievers with deep language models.

Tevatron Tevatron is a simple and efficient toolkit for training and running dense retrievers with deep language models. The toolkit has a modularized

texttron 193 Jan 04, 2023
Natural Language Processing Specialization

Natural Language Processing Specialization In this folder, Natural Language Processing Specialization projects and notes can be found. WHAT I LEARNED

Kaan BOKE 3 Oct 06, 2022
🤗🖼️ HuggingPics: Fine-tune Vision Transformers for anything using images found on the web.

🤗 🖼️ HuggingPics Fine-tune Vision Transformers for anything using images found on the web. Check out the video below for a walkthrough of this proje

Nathan Raw 185 Dec 21, 2022
Ray-based parallel data preprocessing for NLP and ML.

Wrangl Ray-based parallel data preprocessing for NLP and ML. pip install wrangl # for latest pip install git+https://github.com/vzhong/wrangl See exa

Victor Zhong 33 Dec 27, 2022
Blackstone is a spaCy model and library for processing long-form, unstructured legal text

Blackstone Blackstone is a spaCy model and library for processing long-form, unstructured legal text. Blackstone is an experimental research project f

ICLR&D 579 Jan 08, 2023
NLP topic mdel LDA - Gathered from New York Times website

NLP topic mdel LDA - Gathered from New York Times website

1 Oct 14, 2021