DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

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}
}
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition

107 Dec 02, 2022
TorchIO is a Medical image preprocessing and augmentation toolkit for deep learning. Part of the PyTorch Ecosystem.

Medical image preprocessing and augmentation toolkit for deep learning. Part of the PyTorch Ecosystem.

Fernando Pérez-García 1.6k Jan 06, 2023
Deep Learning Package based on TensorFlow

White-Box-Layer is a Python module for deep learning built on top of TensorFlow and is distributed under the MIT license. The project was started in M

YeongHyeon Park 7 Dec 27, 2021
PyTorch code for the paper "Complementarity is the King: Multi-modal and Multi-grained Hierarchical Semantic Enhancement Network for Cross-modal Retrieval".

Complementarity is the King: Multi-modal and Multi-grained Hierarchical Semantic Enhancement Network for Cross-modal Retrieval (M2HSE) PyTorch code fo

Xinlei-Pei 6 Dec 23, 2022
ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels

ROCKET + MINIROCKET ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels. Data Mining and Knowledge D

298 Dec 26, 2022
Auto-updating data to assist in investment to NEPSE

Symbol Ratios Summary Sector LTP Undervalued Bonus % MEGA Strong Commercial Banks 368 5 10 JBBL Strong Development Banks 568 5 10 SIFC Strong Finance

Amit Chaudhary 16 Nov 01, 2022
Applications using the GTN library and code to reproduce experiments in "Differentiable Weighted Finite-State Transducers"

gtn_applications An applications library using GTN. Current examples include: Offline handwriting recognition Automatic speech recognition Installing

Facebook Research 68 Dec 29, 2022
Pyeventbus: a publish/subscribe event bus

pyeventbus pyeventbus is a publish/subscribe event bus for Python 2.7. simplifies the communication between python classes decouples event senders and

15 Apr 21, 2022
Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data

Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data This is the official PyTorch implementation of the SeCo paper: @articl

ElementAI 101 Dec 12, 2022
Dynamic wallpaper generator.

Wiki • About • Installation About This project is a dynamic wallpaper changer. It waits untill you turn on the music, downloads album cover if it's po

3 Sep 18, 2021
Miscellaneous and lightweight network tools

Network Tools Collection of miscellaneous and lightweight network tools to simplify daily operations, administration, and troubleshooting of networks.

Nicholas Russo 22 Mar 22, 2022
Compute descriptors for 3D point cloud registration using a multi scale sparse voxel architecture

MS-SVConv : 3D Point Cloud Registration with Multi-Scale Architecture and Self-supervised Fine-tuning Compute features for 3D point cloud registration

42 Jul 25, 2022
Cossim - Sharpened Cosine Distance implementation in PyTorch

Sharpened Cosine Distance PyTorch implementation of the Sharpened Cosine Distanc

Istvan Fehervari 10 Mar 22, 2022
PaSST: Efficient Training of Audio Transformers with Patchout

PaSST: Efficient Training of Audio Transformers with Patchout This is the implementation for Efficient Training of Audio Transformers with Patchout Pa

165 Dec 26, 2022
Message Passing on Cell Complexes

CW Networks This repository contains the code used for the papers Weisfeiler and Lehman Go Cellular: CW Networks (Under review) and Weisfeiler and Leh

Twitter Research 108 Jan 05, 2023
Using deep actor-critic model to learn best strategies in pair trading

Deep-Reinforcement-Learning-in-Stock-Trading Using deep actor-critic model to learn best strategies in pair trading Abstract Partially observed Markov

281 Dec 09, 2022
How Effective is Incongruity? Implications for Code-mix Sarcasm Detection.

Code for the paper: How Effective is Incongruity? Implications for Code-mix Sarcasm Detection - ICON ACL 2021

2 Jun 05, 2022
A lightweight deep network for fast and accurate optical flow estimation.

FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation The official PyTorch implementation of FastFlowNet (ICRA 2021). Authors: Lingtong

Tone 161 Jan 03, 2023
Official Pytorch implementation of "Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video", CVPR 2021

TCMR: Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video Qualtitative result Paper teaser video Introduction This r

Hongsuk Choi 215 Jan 06, 2023
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19

2s-AGCN Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19 Note PyTorch version should be 0.3! For PyTor

LShi 547 Dec 26, 2022