[Preprint] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

Overview

Chasing Sparsity in Vision Transformers: An End-to-End Exploration

License: MIT

Codes for [Preprint] Chasing Sparsity in Vision Transformers: An End-to-End Exploration.

Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

Overall Results

Extensive results on ImageNet with diverse ViT backbones validate the effectiveness of our proposals which obtain significantly reduced computational cost and almost unimpaired generalization. Perhaps most surprisingly, we find that the proposed sparse (co-)training can even improve the ViT accuracy rather than compromising it, making sparsity a tantalizing “free lunch”. For example, our sparsified DeiT-Small at (5%, 50%) sparsity for (data, architecture), improves 0.28% top-1 accuracy, and meanwhile enjoys 49.32% FLOPs and 4.40% running time savings.

Proposed Framework of SViTE

Implementations of SViTE

Set Environment

conda create -n vit python=3.6

pip install torch==1.7.1+cu101 torchvision==0.8.2+cu101 torchaudio==0.7.2 -f https://download.pytorch.org/whl/torch_stable.html

pip install tqdm scipy timm

git clone https://github.com/NVIDIA/apex

cd apex

pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

pip install -v --disable-pip-version-check --no-cache-dir ./

Cmd

Command for unstructured sparsity, i.e., SViTE.

  • SViTE-Small
bash cmd/ vm/0426/vm1.sh 0,1,2,3,4,5,6,7

Details

CUDA_VISIBLE_DEVICES=$1 \
python -m torch.distributed.launch \
    --nproc_per_node=8 \
    --use_env main.py \
    --model deit_small_patch16_224 \
    --epochs 600 \
    --batch-size 64 \
    --data-path ../../imagenet \
    --output_dir ./small_dst_uns_0426_vm1 \
    --dist_url tcp://127.0.0.1:23305 \
    --sparse_init fixed_ERK \
    --density 0.4 \
    --update_frequency 15000 \
    --growth gradient \
    --death magnitude \
    --redistribution none
  • SViTE-Base
bash cmd/ vm/0426/vm3.sh 0,1,2,3,4,5,6,7

Details

CUDA_VISIBLE_DEVICES=$1 \
python -m torch.distributed.launch \
    --nproc_per_node=8 \
    --use_env main.py \
    --model deit_base_patch16_224 \
    --epochs 600 \
    --batch-size 128 \
    --data-path ../../imagenet \
    --output_dir ./base_dst_uns_0426_vm3 \
    --dist_url tcp://127.0.0.1:23305 \
    --sparse_init fixed_ERK \
    --density 0.4 \
    --update_frequency 7000 \
    --growth gradient \
    --death magnitude \
    --redistribution none

Remark. More commands can be found under the "cmd" folder.

Command for structured sparsity is comming soon!

Pre-traiend SViTE Models.

  1. SViTE-Base with 40% structural sparsity ACC=82.22

https://www.dropbox.com/s/ix7mmduvf0wlc4b/deit_base_structure_40_82.22.pth?dl=0

  1. SViTE-Base with 40% unstructured sparsity ACC=81.56

https://www.dropbox.com/s/vltm4piwn9cwsop/deit_base_unstructure_40_81.56.pth?dl=0

  1. SViTE-Small with 50% unstructued sparsity and 5% data sparisity ACC=80.18

https://www.dropbox.com/s/kofps21g857wlbt/deit_small_unstructure_50_sparseinput_0.95_80.18.pth?dl=0

  1. SViTE-Small with 50% unstructured sparsity and 10% data sparsity ACC=79.91

https://www.dropbox.com/s/bdhpc6nfrwahcuc/deit_small_unstructure_50_sparseinput_0.90_79.91.pth?dl=0

Citation

@misc{chen2021chasing,
      title={Chasing Sparsity in Vision Transformers:An End-to-End Exploration}, 
      author={Tianlong Chen and Yu Cheng and Zhe Gan and Lu Yuan and Lei Zhang and Zhangyang Wang},
      year={2021},
      eprint={2106.04533},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Acknowledge Related Repos

ViT : https://github.com/jeonsworld/ViT-pytorch

ViT : https://github.com/google-research/vision_transformer

Rig : https://github.com/google-research/rigl

DeiT: https://github.com/facebookresearch/deit

Owner
VITA
Visual Informatics Group @ University of Texas at Austin
VITA
This repo contains the official code and pre-trained models for the Dynamic Vision Transformer (DVT).

Dynamic-Vision-Transformer (Pytorch) This repo contains the official code and pre-trained models for the Dynamic Vision Transformer (DVT). Not All Ima

210 Dec 18, 2022
Official implementation for paper Render In-between: Motion Guided Video Synthesis for Action Interpolation

Render In-between: Motion Guided Video Synthesis for Action Interpolation [Paper] [Supp] [arXiv] [4min Video] This is the official Pytorch implementat

8 Oct 27, 2022
Optimus: the first large-scale pre-trained VAE language model

Optimus: the first pre-trained Big VAE language model This repository contains source code necessary to reproduce the results presented in the EMNLP 2

314 Dec 19, 2022
Implementation of CVPR 2020 Dual Super-Resolution Learning for Semantic Segmentation

Dual super-resolution learning for semantic segmentation 2021-01-02 Subpixel Update Happy new year! The 2020-12-29 update of SISR with subpixel conv p

Sam 79 Nov 24, 2022
Semantic graph parser based on Categorial grammars

Lambekseq "Everyone who failed Greek or Latin hates it." This package is for proving theorems in Categorial grammars (CG) and constructing semantic gr

10 Aug 19, 2022
Implementation of Feedback Transformer in Pytorch

Feedback Transformer - Pytorch Simple implementation of Feedback Transformer in Pytorch. They improve on Transformer-XL by having each token have acce

Phil Wang 93 Oct 04, 2022
Implementation of the paper "Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning"

Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning This is the implementation of the paper "Self-Promoted Prototype Refinement

Kai Zhu 78 Dec 02, 2022
A lightweight tool to get an AI Infrastructure Stack up in minutes not days.

K3ai will take care of setup K8s for You, deploy the AI tool of your choice and even run your code on it.

k3ai 105 Dec 04, 2022
Reinforcement Learning via Supervised Learning

Reinforcement Learning via Supervised Learning Installation Run pip install -e . in an environment with Python = 3.7.0, 3.9. The code depends on MuJ

Scott Emmons 49 Nov 28, 2022
PyBrain - Another Python Machine Learning Library.

PyBrain -- the Python Machine Learning Library =============================================== INSTALLATION ------------ Quick answer: make sure you

2.8k Dec 31, 2022
TensorFlow implementation of Barlow Twins (Barlow Twins: Self-Supervised Learning via Redundancy Reduction)

Barlow-Twins-TF This repository implements Barlow Twins (Barlow Twins: Self-Supervised Learning via Redundancy Reduction) in TensorFlow and demonstrat

Sayak Paul 36 Sep 14, 2022
Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs

Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs MATLAB implementation of the paper: P. Mercado, F. Tudisco, and M. Hein,

Pedro Mercado 6 May 26, 2022
This is the dataset and code release of the OpenRooms Dataset.

This is the dataset and code release of the OpenRooms Dataset.

Visual Intelligence Lab of UCSD 95 Jan 08, 2023
A Tensorflow implementation of BicycleGAN.

BicycleGAN implementation in Tensorflow As part of the implementation series of Joseph Lim's group at USC, our motivation is to accelerate (or sometim

Cognitive Learning for Vision and Robotics (CLVR) lab @ USC 97 Dec 02, 2022
Repo for paper "Dynamic Placement of Rapidly Deployable Mobile Sensor Robots Using Machine Learning and Expected Value of Information"

Repo for paper "Dynamic Placement of Rapidly Deployable Mobile Sensor Robots Using Machine Learning and Expected Value of Information" Notes I probabl

Berkeley Expert System Technologies Lab 0 Jul 01, 2021
Hand Gesture Volume Control | Open CV | Computer Vision

Gesture Volume Control Hand Gesture Volume Control | Open CV | Computer Vision Use gesture control to change the volume of a computer. First we look i

Jhenil Parihar 3 Jun 15, 2022
Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation

Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation

Bae, Gwangbin 95 Jan 04, 2023
EfficientNetV2 implementation using PyTorch

EfficientNetV2-S implementation using PyTorch Train Steps Configure imagenet path by changing data_dir in train.py python main.py --benchmark for mode

Jahongir Yunusov 86 Dec 29, 2022
PyTorch implementation of Off-policy Learning in Two-stage Recommender Systems

Off-Policy-2-Stage This repo provides a PyTorch implementation of the MovieLens experiments for the following paper: Off-policy Learning in Two-stage

Jiaqi Ma 25 Dec 12, 2022
A benchmark dataset for mesh multi-label-classification based on cube engravings introduced in MeshCNN

Double Cube Engravings This script creates a dataset for multi-label mesh clasification, with an intentionally difficult setup for point cloud classif

Yotam Erel 1 Nov 30, 2021