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

A general 3D Object Detection codebase in PyTorch.

Updated for TTS(CE) = Also Known as TTN V3. The code requires the first server to be 'ttn' protocol.

Pytorch implementation of MixNMatch

Python package to generate image embeddings with CLIP without PyTorch/TensorFlow

DNA-RECON { Automatic Web Reconnaissance Tool }

MARS: Learning Modality-Agnostic Representation for Scalable Cross-media Retrieva

DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generative Transformers

Official pytorch implementation of DeformSyncNet: Deformation Transfer via Synchronized Shape Deformation Spaces

An implementation of based on pytorch and mmcv

The original weights of some Caffe models, ported to PyTorch.

Pytorch implementation of the AAAI 2022 paper "Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification"

Empirical Study of Transformers for Source Code & A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code

Keras implementation of Normalizer-Free Networks and SGD - Adaptive Gradient Clipping

A Comprehensive Empirical Study of Vision-Language Pre-trained Model for Supervised Cross-Modal Retrieval

PyTorch implementation of a collections of scalable Video Transformer Benchmarks.

CS583: Deep Learning

StellarGraph - Machine Learning on Graphs

A python script to lookup Passport Index Dataset

Convert onnx models to pytorch.

tsflex - feature-extraction benchmarking