DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Related tags

Deep Learningcomputer-visiondeep-learningimage-classificationvision-transformers
Overview

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Created by Yongming Rao, Wenliang Zhao, Benlin Liu, Jiwen Lu, Jie Zhou, Cho-Jui Hsieh

This repository contains PyTorch implementation for DynamicViT.

We introduce a dynamic token sparsification framework to prune redundant tokens in vision transformers progressively and dynamically based on the input:

intro

Our code is based on pytorch-image-models, DeiT and LV-ViT

[Project Page] [arXiv]

Model Zoo

We provide our DynamicViT models pretrained on ImageNet:

name arch rho [email protected] [email protected] FLOPs url
DynamicViT-256/0.7 deit_256 0.7 76.532 93.118 1.3G Google Drive / Tsinghua Cloud
DynamicViT-384/0.7 deit_small 0.7 79.316 94.676 2.9G Google Drive / Tsinghua Cloud
DynamicViT-LV-S/0.5 lvvit_s 0.5 81.970 95.756 3.7G Google Drive / Tsinghua Cloud
DynamicViT-LV-S/0.7 lvvit_s 0.7 83.076 96.252 4.6G Google Drive / Tsinghua Cloud
DynamicViT-LV-M/0.7 lvvit_m 0.7 83.816 96.584 8.5G Google Drive / Tsinghua Cloud

Usage

Requirements

  • torch>=1.7.0
  • torchvision>=0.8.1
  • timm==0.4.5

Data preparation: download and extract ImageNet images from http://image-net.org/. The directory structure should be

│ILSVRC2012/
├──train/
│  ├── n01440764
│  │   ├── n01440764_10026.JPEG
│  │   ├── n01440764_10027.JPEG
│  │   ├── ......
│  ├── ......
├──val/
│  ├── n01440764
│  │   ├── ILSVRC2012_val_00000293.JPEG
│  │   ├── ILSVRC2012_val_00002138.JPEG
│  │   ├── ......
│  ├── ......

Model preparation: download pre-trained DeiT and LV-ViT models for training DynamicViT:

sh download_pretrain.sh

Demo

We provide a Jupyter notebook where you can run the visualization of DynamicViT.

To run the demo, you need to install matplotlib.

demo

Evaluation

To evaluate a pre-trained DynamicViT model on ImageNet val with a single GPU, run:

python infer.py --data-path /path/to/ILSVRC2012/ --arch arch_name --model-path /path/to/model --base_rate 0.7

Training

To train DynamicViT models on ImageNet, run:

DeiT-small

python -m torch.distributed.launch --nproc_per_node=8 --use_env main_dynamic_vit.py  --output_dir logs/dynamic-vit_deit-small --arch deit_small --input-size 224 --batch-size 96 --data-path /path/to/ILSVRC2012/ --epochs 30 --dist-eval --distill --base_rate 0.7

LV-ViT-S

python -m torch.distributed.launch --nproc_per_node=8 --use_env main_dynamic_vit.py  --output_dir logs/dynamic-vit_lvvit-s --arch lvvit_s --input-size 224 --batch-size 64 --data-path /path/to/ILSVRC2012/ --epochs 30 --dist-eval --distill --base_rate 0.7

LV-ViT-M

python -m torch.distributed.launch --nproc_per_node=8 --use_env main_dynamic_vit.py  --output_dir logs/dynamic-vit_lvvit-m --arch lvvit_m --input-size 224 --batch-size 48 --data-path /path/to/ILSVRC2012/ --epochs 30 --dist-eval --distill --base_rate 0.7

You can train models with different keeping ratio by adjusting base_rate. DynamicViT can also achieve comparable performance with only 15 epochs training (around 0.1% lower accuracy).

License

MIT License

Citation

If you find our work useful in your research, please consider citing:

@article{rao2021dynamicvit,
  title={DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification},
  author={Rao, Yongming and Zhao, Wenliang and Liu, Benlin and Lu, Jiwen and Zhou, Jie and Hsieh, Cho-Jui},
  journal={arXiv preprint arXiv:2106.02034},
  year={2021}
}
Owner
Yongming Rao
Yongming Rao
GitHub Repository https://dynamicvit.ivg-research.xyz/
Global Filter Networks for Image Classification

Global Filter Networks for Image Classification Created by Yongming Rao, Wenliang Zhao, Zheng Zhu, Jiwen Lu, Jie Zhou This repository contains PyTorch

Yongming Rao 273 Dec 26, 2022
Code samples for my book "Neural Networks and Deep Learning"

Code samples for "Neural Networks and Deep Learning" This repository contains code samples for my book on "Neural Networks and Deep Learning". The cod

Michael Nielsen 13.9k Dec 26, 2022
Stochastic Tensor Optimization for Robot Motion - A GPU Robot Motion Toolkit

STORM Stochastic Tensor Optimization for Robot Motion - A GPU Robot Motion Toolkit [Install Instructions] [Paper] [Website] This package contains code

NVIDIA Research Projects 101 Dec 12, 2022
Course on computational design, non-linear optimization, and dynamics of soft systems at UIUC.

Computational Design and Dynamics of Soft Systems · This is a repository that contains the source code for generating the lecture notes, handouts, exe

Tejaswin Parthasarathy 4 Jul 21, 2022
Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis (CVPR2022)

Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis Multi-View Consistent Generative Adversarial Networks for 3D-aware

Xuanmeng Zhang 78 Dec 10, 2022
Deep Watershed Transform for Instance Segmentation

Deep Watershed Transform Performs instance level segmentation detailed in the following paper: Min Bai and Raquel Urtasun, Deep Watershed Transformati

193 Nov 20, 2022
H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.

H2O H2O is an in-memory platform for distributed, scalable machine learning. H2O uses familiar interfaces like R, Python, Scala, Java, JSON and the Fl

H2O.ai 6.1k Jan 05, 2023
Semantic similarity computation with different state-of-the-art metrics

Semantic similarity computation with different state-of-the-art metrics Description • Installation • Usage • License Description TaxoSS is a semantic

6 Jun 22, 2022
TorchMetrics is a collection of 25+ PyTorch metrics implementations and an easy-to-use API to create custom metrics.

Machine learning metrics for distributed, scalable PyTorch applications.

Pytorch Lightning 1.2k Jan 06, 2023
Pytorch implementation of our paper under review -- 1xN Pattern for Pruning Convolutional Neural Networks

1xN Pattern for Pruning Convolutional Neural Networks (paper) . This is Pytorch re-implementation of "1xN Pattern for Pruning Convolutional Neural Net

Mingbao Lin (林明宝) 29 Nov 29, 2022
Code for our paper "Graph Pre-training for AMR Parsing and Generation" in ACL2022

AMRBART An implementation for ACL2022 paper "Graph Pre-training for AMR Parsing and Generation". You may find our paper here (Arxiv). Requirements pyt

xfbai 60 Jan 03, 2023
StyleGAN2-ada for practice

This version of the newest PyTorch-based StyleGAN2-ada is intended mostly for fellow artists, who rarely look at scientific metrics, but rather need a working creative tool. Tested on Python 3.7 + Py

vadim epstein 170 Nov 16, 2022
PyTorch implementation of DeepLab v2 on COCO-Stuff / PASCAL VOC

DeepLab with PyTorch This is an unofficial PyTorch implementation of DeepLab v2 [1] with a ResNet-101 backbone. COCO-Stuff dataset [2] and PASCAL VOC

Kazuto Nakashima 995 Jan 08, 2023
A Comparative Framework for Multimodal Recommender Systems

Cornac Cornac is a comparative framework for multimodal recommender systems. It focuses on making it convenient to work with models leveraging auxilia

Preferred.AI 671 Jan 03, 2023
VD-BERT: A Unified Vision and Dialog Transformer with BERT

VD-BERT: A Unified Vision and Dialog Transformer with BERT PyTorch Code for the following paper at EMNLP2020: Title: VD-BERT: A Unified Vision and Dia

Salesforce 44 Nov 01, 2022
Elegy is a framework-agnostic Trainer interface for the Jax ecosystem.

Elegy Elegy is a framework-agnostic Trainer interface for the Jax ecosystem. Main Features Easy-to-use: Elegy provides a Keras-like high-level API tha

435 Dec 30, 2022
This is a model to classify Vietnamese sign language using Motion history image (MHI) algorithm and CNN.

Vietnamese sign lagnuage recognition using MHI and CNN This is a model to classify Vietnamese sign language using Motion history image (MHI) algorithm

Phat Pham 3 Feb 24, 2022
Unsupervised Video Interpolation using Cycle Consistency

Unsupervised Video Interpolation using Cycle Consistency Project | Paper | YouTube Unsupervised Video Interpolation using Cycle Consistency Fitsum A.

NVIDIA Corporation 100 Nov 30, 2022
Guided Internet-delivered Cognitive Behavioral Therapy Adherence Forecasting

Guided Internet-delivered Cognitive Behavioral Therapy Adherence Forecasting #Dataset The folder "Dataset" contains the dataset use in this work and m

0 Jan 08, 2022
Imaging, analysis, and simulation software for radio interferometry

ehtim (eht-imaging) Python modules for simulating and manipulating VLBI data and producing images with regularized maximum likelihood methods. This ve

Andrew Chael 5.2k Dec 28, 2022