[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
PyTorch implementation for 3D human pose estimation

Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach This repository is the PyTorch implementation for the network presented in:

Xingyi Zhou 579 Dec 22, 2022
Nested cross-validation is necessary to avoid biased model performance in embedded feature selection in high-dimensional data with tiny sample sizes

Pruner for nested cross-validation - Sphinx-Doc Nested cross-validation is necessary to avoid biased model performance in embedded feature selection i

1 Dec 15, 2021
Only works with the dashboard version / branch of jesse

Jesse optuna Only works with the dashboard version / branch of jesse. The config.yml should be self-explainatory. Installation # install from git pip

Markus K. 8 Dec 04, 2022
Implementation for the paper: Invertible Denoising Network: A Light Solution for Real Noise Removal (CVPR2021).

Invertible Image Denoising This is the PyTorch implementation of paper: Invertible Denoising Network: A Light Solution for Real Noise Removal (CVPR 20

157 Dec 25, 2022
Perfect implement. Model shared. x0.5 (Top1:60.646) and 1.0x (Top1:69.402).

Shufflenet-v2-Pytorch Introduction This is a Pytorch implementation of faceplusplus's ShuffleNet-v2. For details, please read the following papers:

423 Dec 07, 2022
In the AI for TSP competition we try to solve optimization problems using machine learning.

AI for TSP Competition Goal In the AI for TSP competition we try to solve optimization problems using machine learning. The competition will be hosted

Paulo da Costa 11 Nov 27, 2022
Attention for PyTorch with Linear Memory Footprint

Attention for PyTorch with Linear Memory Footprint Unofficially implements https://arxiv.org/abs/2112.05682 to get Linear Memory Cost on Attention (+

11 Jan 09, 2022
Deep learning model for EEG artifact removal

DeepSeparator Introduction Electroencephalogram (EEG) recordings are often contaminated with artifacts. Various methods have been developed to elimina

23 Dec 21, 2022
Code for "Long Range Probabilistic Forecasting in Time-Series using High Order Statistics"

Long Range Probabilistic Forecasting in Time-Series using High Order Statistics This is the code produced as part of the paper Long Range Probabilisti

16 Dec 06, 2022
codes for "Scheduled Sampling Based on Decoding Steps for Neural Machine Translation" (long paper of EMNLP-2022)

Scheduled Sampling Based on Decoding Steps for Neural Machine Translation (EMNLP-2021 main conference) Contents Overview Background Quick to Use Furth

Adaxry 13 Jul 25, 2022
This app is a simple example of using Strealit to create a financial data web app.

Streamlit Demo: Finance Chart This app is a simple example of using Streamlit to create a financial data web app. This demo use streamlit, pandas and

91 Jan 02, 2023
A free, multiplatform SDK for real-time facial motion capture using blendshapes, and rigid head pose in 3D space from any RGB camera, photo, or video.

mocap4face by Facemoji mocap4face by Facemoji is a free, multiplatform SDK for real-time facial motion capture based on Facial Action Coding System or

Facemoji 591 Dec 27, 2022
Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding

2D-TAN (Optimized) Introduction This is an optimized re-implementation repository for AAAI'2020 paper: Learning 2D Temporal Localization Networks for

Joya Chen 112 Dec 31, 2022
An open software package to develop BCI based brain and cognitive computing technology for recognizing user's intention using deep learning

An open software package to develop BCI based brain and cognitive computing technology for recognizing user's intention using deep learning

deepbci 272 Jan 08, 2023
Source-to-Source Debuggable Derivatives in Pure Python

Tangent Tangent is a new, free, and open-source Python library for automatic differentiation. Existing libraries implement automatic differentiation b

Google 2.2k Jan 01, 2023
Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness

Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness Code for Paper "Imbalanced Gradients: A Subtle Cause of Overestimated Adv

Hanxun Huang 11 Nov 30, 2022
An implementation of the methods presented in Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data.

An implementation of the methods presented in Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data.

Andrew Jesson 9 Apr 04, 2022
PyTorch implementation of an end-to-end Handwritten Text Recognition (HTR) system based on attention encoder-decoder networks

AttentionHTR PyTorch implementation of an end-to-end Handwritten Text Recognition (HTR) system based on attention encoder-decoder networks. Scene Text

Dmitrijs Kass 31 Dec 22, 2022
Code for BMVC2021 paper "Boundary Guided Context Aggregation for Semantic Segmentation"

Boundary-Guided-Context-Aggregation Boundary Guided Context Aggregation for Semantic Segmentation Haoxiang Ma, Hongyu Yang, Di Huang In BMVC'2021 Pape

Haoxiang Ma 31 Jan 08, 2023
Generate image analogies using neural matching and blending

neural image analogies This is basically an implementation of this "Image Analogies" paper, In our case, we use feature maps from VGG16. The patch mat

Adam Wentz 3.5k Jan 08, 2023