DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Last update: Jan 01, 2023

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:

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.

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}
}

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Related tags

Overview

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Model Zoo

Usage

Requirements

Demo

Evaluation

Training

License

Citation

Owner

Yongming Rao

N-RPG - Novel role playing game da turfu

A minimalist tool to display a network graph.

Tweesent-back - Tweesent backend uses fastAPI as the web framework

Code associated with the paper "Deep Optics for Single-shot High-dynamic-range Imaging"

Collects many various multi-modal transformer architectures, including image transformer, video transformer, image-language transformer, video-language transformer and related datasets

MARE - Multi-Attribute Relation Extraction

[ACMMM 2021, Oral] Code release for "Elastic Tactile Simulation Towards Tactile-Visual Perception"

Official Code Implementation of the paper : XAI for Transformers: Better Explanations through Conservative Propagation

SPRING is a seq2seq model for Text-to-AMR and AMR-to-Text (AAAI2021).

Bayesian regularization for functional graphical models.

Synthesizing Long-Term 3D Human Motion and Interaction in 3D in CVPR2021

A python software that can help blind people find things like laptops, phones, etc the same way a guide dog guides a blind person in finding his way.

Estimation of human density in a closed space using deep learning.

CenterPoint 3D Object Detection and Tracking using center points in the bird-eye view.

Real-time ground filtering algorithm of cloud points acquired using Terrestrial Laser Scanner (TLS)

Invasive Plant Species Identification

PassAPI is a password generator in hash format and fully developed in Python, with the aim of teaching how to handle and build

Sample code from the Neural Networks from Scratch book.

an implementation of Revisiting Adaptive Convolutions for Video Frame Interpolation using PyTorch

Disturbing Target Values for Neural Network regularization: attacking the loss layer to prevent overfitting