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

Expressive Power of Invariant and Equivaraint Graph Neural Networks (ICLR 2021)

Randomized Correspondence Algorithm for Structural Image Editing

FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes

PyMatting: A Python Library for Alpha Matting

This is the reference implementation for "Coresets via Bilevel Optimization for Continual Learning and Streaming"

🚀 An end-to-end ML applications using PyTorch, W&B, FastAPI, Docker, Streamlit and Heroku

Training and Evaluation Code for Neural Volumes

Code for LIGA-Stereo Detector, ICCV'21

FEMDA: Robust classification with Flexible Discriminant Analysis in heterogeneous data

A machine learning project which can detect and predict the skin disease through image recognition.

Human annotated noisy labels for CIFAR-10 and CIFAR-100.

This repository contains the code for the binaural-detection model used in the publication arXiv:2111.04637

Explainable Medical ImageSegmentation via GenerativeAdversarial Networks andLayer-wise Relevance Propagation

automatic color-grading

A python library for highly configurable transformers - easing model architecture search and experimentation.

GB-CosFace: Rethinking Softmax-based Face Recognition from the Perspective of Open Set Classification

Pytorch code for "Text-Independent Speaker Verification Using 3D Convolutional Neural Networks".

PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility

In this work, we will implement some basic but important algorithm of machine learning step by step.

PyTorch implementation of a Real-ESRGAN model trained on custom dataset