As-ViT: Auto-scaling Vision Transformers without Training

Overview

As-ViT: Auto-scaling Vision Transformers without Training [PDF]

MIT licensed

Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wang, Denny Zhou

In ICLR 2022.

Note: We implemented topology search (sec. 3.3) and scaling (sec. 3.4) in this code base in PyTorch. Our training code is based on Tensorflow and Keras on TPU, which will be released soon.

Overview

We present As-ViT, a framework that unifies the automatic architecture design and scaling for ViT (vision transformer), in a training-free strategy.

Highlights:

  • Trainig-free ViT Architecture Design: we design a "seed" ViT topology by leveraging a training-free search process. This extremely fast search is fulfilled by our comprehensive study of ViT's network complexity (length distorsion), yielding a strong Kendall-tau correlation with ground-truth accuracies.
  • Trainig-free ViT Architecture Scaling: starting from the "seed" topology, we automate the scaling rule for ViTs by growing widths/depths to different ViT layers. This will generate a series of architectures with different numbers of parameters in a single run.
  • Efficient ViT Training via Progressive Tokenization: we observe that ViTs can tolerate coarse tokenization in early training stages, and further propose to train ViTs faster and cheaper with a progressive tokenization strategy.

teaser
Left: Length Distortion shows a strong correlation with ViT's accuracy. Middle: Auto scaling rule of As-ViT. Right: Progressive re-tokenization for efficient ViT training.

Prerequisites

  • Ubuntu 18.04
  • Python 3.6.9
  • CUDA 11.0 (lower versions may work but were not tested)
  • NVIDIA GPU + CuDNN v7.6

This repository has been tested on V100 GPU. Configurations may need to be changed on different platforms.

Installation

  • Clone this repo:
git clone https://github.com/VITA-Grou/AsViT.git
cd AsViT
  • Install dependencies:
pip install -r requirements.txt

1. Seed As-ViT Topology Search

CUDA_VISIBLE_DEVICES=0 python ./search/reinforce.py --save_dir ./output/REINFORCE-imagenet --data_path /path/to/imagenet

This job will return you a seed topology. For example, our search seed topology is 8,2,3|4,1,2|4,1,4|4,1,6|32, which can be explained as below:

Stage1 Stage2 Stage3 Stage4 Head
Kernel K1 Split S1 Expansion E1 Kernel K2 Split S2 Expansion E2 Kernel K3 Split S3 Expansion E3 Kernel K4 Split S4 Expansion E4
8 2 3 4 1 2 4 1 4 4 1 6 32

2. Scaling

CUDA_VISIBLE_DEVICES=0 python ./search/grow.py --save_dir ./output/GROW-imagenet \
--arch "[arch]" --data_path /path/to/imagenet

Here [arch] is the seed topology (output from step 1 above). This job will return you a series of topologies. For example, our largest topology (As-ViT Large) is 8,2,3,5|4,1,2,2|4,1,4,5|4,1,6,2|32,180, which can be explained as below:

Stage1 Stage2 Stage3 Stage4 Head Initial Hidden Size
Kernel K1 Split S1 Expansion E1 Layers L1 Kernel K2 Split S2 Expansion E2 Layers L2 Kernel K3 Split S3 Expansion E3 Layers L3 Kernel K4 Split S4 Expansion E4 Layers L4
8 2 3 5 4 1 2 2 4 1 4 5 4 1 6 2 32 180

3. Evaluation

Tensorflow and Keras code for training on TPU. To be released soon.

Citation

@inproceedings{chen2021asvit,
  title={Auto-scaling Vision Transformers without Training},
  author={Chen, Wuyang and Huang, Wei and Du, Xianzhi and Song, Xiaodan and Wang, Zhangyang and Zhou, Denny},
  booktitle={International Conference on Learning Representations},
  year={2022}
}
Owner
VITA
Visual Informatics Group @ University of Texas at Austin
VITA
Red Team tool for exfiltrating files from a target's Google Drive that you have access to, via Google's API.

GD-Thief Red Team tool for exfiltrating files from a target's Google Drive that you(the attacker) has access to, via the Google Drive API. This includ

Antonio Piazza 39 Dec 27, 2022
links and status of cool gradio demos

awesome-demos This is a list of some wonderful demos & applications built with Gradio. Here's how to contribute yours! 🖊️ Natural language processing

Gradio 96 Dec 30, 2022
A pytorch implementation of Reading Wikipedia to Answer Open-Domain Questions.

DrQA A pytorch implementation of the ACL 2017 paper Reading Wikipedia to Answer Open-Domain Questions (DrQA). Reading comprehension is a task to produ

Runqi Yang 394 Nov 08, 2022
Code for our paper Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation

CorDA Code for our paper Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation Prerequisite Please create and activate the follo

Qin Wang 60 Nov 30, 2022
Implementation of: "Exploring Randomly Wired Neural Networks for Image Recognition"

RandWireNN Unofficial PyTorch Implementation of: Exploring Randomly Wired Neural Networks for Image Recognition. Results Validation result on Imagenet

Seung-won Park 684 Nov 02, 2022
PHOTONAI is a high level python API for designing and optimizing machine learning pipelines.

PHOTONAI is a high level python API for designing and optimizing machine learning pipelines. We've created a system in which you can easily select and

Medical Machine Learning Lab - University of Münster 57 Nov 12, 2022
Normalizing Flows with a resampled base distribution

Resampling Base Distributions of Normalizing Flows Normalizing flows are a popular class of models for approximating probability distributions. Howeve

Vincent Stimper 24 Nov 03, 2022
🎃 Core identification module of AI powerful point reading system platform.

ppReader-Kernel Intro Core identification module of AI powerful point reading system platform. Usage 硬件: Windows10、GPU:nvdia GTX 1060 、普通RBG相机 软件: con

CrashKing 1 Jan 11, 2022
An easy-to-use app to visualise attentions of various VQA models.

Ask Me Anything: A tool for visualising Visual Question Answering (AMA) An easy-to-use app to visualise attentions of various VQA models. Please click

Apoorve 37 Nov 13, 2022
Tensorflow 2 implementation of our high quality frame interpolation neural network

FILM: Frame Interpolation for Large Scene Motion Project | Paper | YouTube | Benchmark Scores Tensorflow 2 implementation of our high quality frame in

Google Research 1.6k Dec 28, 2022
Boundary-aware Transformers for Skin Lesion Segmentation

Boundary-aware Transformers for Skin Lesion Segmentation Introduction This is an official release of the paper Boundary-aware Transformers for Skin Le

Jiacheng Wang 79 Dec 16, 2022
Code accompanying the paper on "An Empirical Investigation of Domain Generalization with Empirical Risk Minimizers" published at NeurIPS, 2021

Code for "An Empirical Investigation of Domian Generalization with Empirical Risk Minimizers" (NeurIPS 2021) Motivation and Introduction Domain Genera

Meta Research 15 Dec 27, 2022
PyTorch code for SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised DA

PyTorch Code for SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation Viraj Prabhu, Shivam Khare, Deeks

Viraj Prabhu 46 Dec 24, 2022
PyTorch Implementation of NCSOFT's FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis

FastPitchFormant - PyTorch Implementation PyTorch Implementation of FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis. Qu

Keon Lee 63 Jan 02, 2023
A set of simple scripts to process the Imagenet-1K dataset as TFRecords and make index files for NVIDIA DALI.

Overview This is a set of simple scripts to process the Imagenet-1K dataset as TFRecords and make index files for NVIDIA DALI. Make TFRecords To run t

8 Nov 01, 2022
EgGateWayGetShell py脚本

EgGateWayGetShell_py 免责声明 由于传播、利用此文所提供的信息而造成的任何直接或者间接的后果及损失,均由使用者本人负责,作者不为此承担任何责任。 使用 python3 eg.py urls.txt 目标 title:锐捷网络-EWEB网管系统 port:4430 漏洞成因 ?p

榆木 61 Nov 09, 2022
A PyTorch implementation of EventProp [https://arxiv.org/abs/2009.08378], a method to train Spiking Neural Networks

Spiking Neural Network training with EventProp This is an unofficial PyTorch implemenation of EventProp, a method to compute exact gradients for Spiki

Pedro Savarese 35 Jul 29, 2022
Pynomial - a lightweight python library for implementing the many confidence intervals for the risk parameter of a binomial model

Pynomial - a lightweight python library for implementing the many confidence intervals for the risk parameter of a binomial model

Demetri Pananos 9 Oct 04, 2022
PyTorch code of "SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks"

SLAPS-GNN This repo contains the implementation of the model proposed in SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks

60 Dec 22, 2022
Duke Machine Learning Winter School: Computer Vision 2022

mlwscv2002 Welcome to the Duke Machine Learning Winter School: Computer Vision 2022! The MLWS-CV includes 3 hands-on training sessions on implementing

Duke + Data Science (+DS) 9 May 25, 2022