Paddle pit - Rethinking Spatial Dimensions of Vision Transformers

Overview

基于Paddle实现PiT ——Rethinking Spatial Dimensions of Vision Transformers,arxiv

  • 官方原版代码(基于PyTorch)pit.

  • 本项目基于 PaddleViT 实现,在其基础上与原版代码实现了更进一步的对齐,并通过完整训练与测试完成对pit_ti模型的复现.

1. 简介

从CNN的成功设计原理出发,作者研究了空间尺寸转换的作用及其在基于Transformer的体系结构上的有效性。

具体来说,类似于CNN的降维原则(随着深度的增加,传统的CNN会增加通道尺寸并减小空间尺寸),作者用实验表明了这同样有利于Transformer的性能提升,并提出了基于池化的Vision Transformer,即PiT(模型示意图如下)。

drawing

PiT 模型示意图

2. 数据集和复现精度

数据集

原文使用的为ImageNet-1k 2012(ILSVRC2012),共1000类,训练集/测试集图片分布:1281167/50000,数据集大小为144GB。

本项目使用的为官方推荐的图片压缩过的更轻量的Light_ILSVRC2012,数据集大小为65GB。其在AI Studio上的地址为:Light_ILSVRC2012_part_0.tarLight_ILSVRC2012_part_1.tar

复现精度

Model 目标精度[email protected] 实现精度[email protected] Image Size batch_size Crop_pct epoch #Params
pit_ti 73.0 73.01 224 256*4GPUs 0.9 300
(+10 COOLDOWN)
4.8M

【注】上表中的实现精度在原版ILSVRC2012验证集上测试得到。 值得一提的是,本项目在Light_ILSVRC2012的验证集上的Validation [email protected]达到了73.17

本项目训练得到的最佳模型参数与训练日志log均存放于output文件夹下。

日志文件说明

本项目通过AI Studio的脚本任务运行,中途中断了4次,因此共有5个日志文件。为了方便检阅,本人手动将log命名为log_开始epoch-结束epoch.txt格式。具体来说:

  • output/log_1-76.txt:epoch1~epoch76。这一版代码定义每10个epoch保存一次模型权重,每2个epoch验证一次,同时若验证精度高于历史精度,则保存为Best_PiT.pdparams,因此在epoch76训练结束但还未验证的时候中断,下一次的训练只能从验证精度最高的epoch74继续训练。

  • output/log_75-142.txt:epoch75~epoch142。从这一版代码开始,新增了每次训练之后都保存一下模型参数为PiT-Latest.pdparams,这样无论哪个epoch训练中断都可以继续训练啦。

  • output/log_143-225.txt:epoch143~epoch225。

  • output/log_226-303.txt:epoch226~epoch303。

  • output/log_304-310.txt:epoch304~epoch310。

  • output/log_eval.txt:使用训练得到的最好模型(epoch308)在原版ILSVRC2012验证集上验证日志。

3. 准备环境

推荐环境配置:

本人环境配置:

  • 硬件:Tesla V100 * 4(由衷感谢百度飞桨平台提供高性能算力支持)

  • PaddlePaddle==2.2.1

  • Python==3.7

4. 快速开始

本项目现已通过脚本任务形式部署到AI Studio上,您可以选择fork下来直接运行sh run.sh,数据集处理等脚本均已部署好。链接:paddle_pit

或者您也可以git本repo在本地运行:

第一步:克隆本项目

git clone https://github.com/hatimwen/paddle_pit.git
cd paddle_pit

第二步:修改参数

请根据实际情况,修改scripts路径下的脚本内容(如:gpu,数据集路径data_path,batch_size等)。

第三步:验证模型

多卡请运行:

sh scripts/run_eval_multi.sh

单卡请运行:

sh scripts/run_eval.sh

第四步:训练模型

多卡请运行:

sh scripts/run_train_multi.sh

单卡请运行:

sh scripts/run_train.sh

第五步:验证预测

python predict.py \
-pretrained='output/Best_PiT' \
-img_path='images/ILSVRC2012_val_00004506.JPEG'

验证图片(类别:藏獒, id: 244)

输出结果为:

class_id: 244, prob: 9.12291145324707

对照ImageNet类别id(ImageNet数据集编号对应的类别内容),可知244为藏獒,预测结果正确。

5.代码结构

|-- paddle_pit
    |-- output              # 日志及模型文件
    |-- configs             # 参数
        |-- pit_ti.yaml
    |-- datasets
        |-- ImageNet1K      # 数据集路径
    |-- scripts             # 运行脚本
        |-- run_train.sh
        |-- run_train_multi.sh
        |-- run_eval.sh
        |-- run_eval_multi.sh
    |-- augment.py          # 数据增强
    |-- config.py           # 最底层配置文件
    |-- datasets.py         # dataset与dataloader
    |-- droppath.py         # droppath定义
    |-- losses.py           # loss定义
    |-- main_multi_gpu.py   # 多卡训练测试代码
    |-- main_single_gpu.py  # 单卡训练测试代码
    |-- mixup.py            # mixup定义
    |-- model_ema.py        # EMA定义
    |-- pit.py              # pit模型结构定义
    |-- random_erasing.py   # random_erasing定义
    |-- regnet.py           # 教师模型定义(本项目并未对此验证,仅作保留)
    |-- transforms.py       # RandomHorizontalFlip定义
    |-- utils.py            # CosineLRScheduler及AverageMeter定义
    |-- README.md
    |-- requirements.txt

6. 参考及引用

@InProceedings{Yuan_2021_ICCV,
    author    = {Yuan, Li and Chen, Yunpeng and Wang, Tao and Yu, Weihao and Shi, Yujun and Jiang, Zi-Hang and Tay, Francis E.H. and Feng, Jiashi and Yan, Shuicheng},
    title     = {Tokens-to-Token ViT: Training Vision Transformers From Scratch on ImageNet},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2021},
    pages     = {558-567}
}

最后,非常感谢百度举办的飞桨论文复现挑战赛(第五期)让本人对Paddle理解更加深刻。 同时也非常感谢朱欤老师团队用Paddle实现的PaddleViT,本项目大部分代码都是从中copy来的,而仅仅实现了其与原版代码训练步骤的进一步对齐与完整的训练过程,但本人也同样受益匪浅! ♥️

Contact

Owner
Hongtao Wen
Hongtao Wen
Reproduces the results of the paper "Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations".

Finite basis physics-informed neural networks (FBPINNs) This repository reproduces the results of the paper Finite Basis Physics-Informed Neural Netwo

Ben Moseley 65 Dec 28, 2022
COD-Rank-Localize-and-Segment (CVPR2021)

COD-Rank-Localize-and-Segment (CVPR2021) Simultaneously Localize, Segment and Rank the Camouflaged Objects Full camouflage fixation training dataset i

JingZhang 52 Dec 20, 2022
LSTC: Boosting Atomic Action Detection with Long-Short-Term Context

LSTC: Boosting Atomic Action Detection with Long-Short-Term Context This Repository contains the code on AVA of our ACM MM 2021 paper: LSTC: Boosting

Tencent YouTu Research 9 Oct 11, 2022
DR-GAN: Automatic Radial Distortion Rectification Using Conditional GAN in Real-Time

DR-GAN: Automatic Radial Distortion Rectification Using Conditional GAN in Real-Time Introduction This is official implementation for DR-GAN (IEEE TCS

Kang Liao 18 Dec 23, 2022
Open-L2O: A Comprehensive and Reproducible Benchmark for Learning to Optimize Algorithms

Open-L2O This repository establishes the first comprehensive benchmark efforts of existing learning to optimize (L2O) approaches on a number of proble

VITA 161 Jan 02, 2023
PyTorch Implementation of Small Lesion Segmentation in Brain MRIs with Subpixel Embedding (ORAL, MICCAIW 2021)

Small Lesion Segmentation in Brain MRIs with Subpixel Embedding PyTorch implementation of Small Lesion Segmentation in Brain MRIs with Subpixel Embedd

22 Oct 21, 2022
The implementation of ICASSP 2020 paper "Pixel-level self-paced learning for super-resolution"

Pixel-level Self-Paced Learning for Super-Resolution This is an official implementaion of the paper Pixel-level Self-Paced Learning for Super-Resoluti

Elon Lin 41 Dec 15, 2022
Implementation for Stankevičiūtė et al. "Conformal time-series forecasting", NeurIPS 2021.

Conformal time-series forecasting Implementation for Stankevičiūtė et al. "Conformal time-series forecasting", NeurIPS 2021. If you use our code in yo

Kamilė Stankevičiūtė 36 Nov 21, 2022
Cross-modal Retrieval using Transformer Encoder Reasoning Networks (TERN). With use of Metric Learning and FAISS for fast similarity search on GPU

Cross-modal Retrieval using Transformer Encoder Reasoning Networks This project reimplements the idea from "Transformer Reasoning Network for Image-Te

Minh-Khoi Pham 5 Nov 05, 2022
A note taker for NVDA. Allows the user to create, edit, view, manage and export notes to different formats.

Quick Notetaker add-on for NVDA The Quick Notetaker add-on is a wonderful tool which allows writing notes quickly and easily anytime and from any app

5 Dec 06, 2022
Distributed Evolutionary Algorithms in Python

DEAP DEAP is a novel evolutionary computation framework for rapid prototyping and testing of ideas. It seeks to make algorithms explicit and data stru

Distributed Evolutionary Algorithms in Python 4.9k Jan 05, 2023
CLEAR algorithm for multi-view data association

CLEAR: Consistent Lifting, Embedding, and Alignment Rectification Algorithm The Matlab, Python, and C++ implementation of the CLEAR algorithm, as desc

MIT Aerospace Controls Laboratory 30 Jan 02, 2023
University of Rochester 2021 Summer REU focusing on music sentiment transfer using CycleGAN

Music-Sentiment-Transfer University of Rochester 2021 Summer REU focusing on music sentiment transfer using CycleGAN Poster: Music Sentiment Transfer

Miles Sigel 2 Jan 24, 2022
Probabilistic Programming and Statistical Inference in PyTorch

PtStat Probabilistic Programming and Statistical Inference in PyTorch. Introduction This project is being developed during my time at Cogent Labs. The

Stefano Peluchetti 109 Nov 26, 2022
A Traffic Sign Recognition Project which can help the driver recognise the signs via text as well as audio. Can be used at Night also.

Traffic-Sign-Recognition In this report, we propose a Convolutional Neural Network(CNN) for traffic sign classification that achieves outstanding perf

Mini Project 64 Nov 19, 2022
Official implementation for the paper "Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection"

Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection PyTorch code release of the paper "Attentive Prototypes for Sour

Deepti Hegde 23 Oct 17, 2022
BEGAN in PyTorch

BEGAN in PyTorch This project is still in progress. If you are looking for the working code, use BEGAN-tensorflow. Requirements Python 2.7 Pillow tqdm

Taehoon Kim 260 Dec 07, 2022
PASSL包含 SimCLR,MoCo,BYOL,CLIP等基于对比学习的图像自监督算法以及 Vision-Transformer,Swin-Transformer,BEiT,CVT,T2T,MLP_Mixer等视觉Transformer算法

PASSL Introduction PASSL is a Paddle based vision library for state-of-the-art Self-Supervised Learning research with PaddlePaddle. PASSL aims to acce

186 Dec 29, 2022
Hidden-Fold Networks (HFN): Random Recurrent Residuals Using Sparse Supermasks

Hidden-Fold Networks (HFN): Random Recurrent Residuals Using Sparse Supermasks by Ángel López García-Arias, Masanori Hashimoto, Masato Motomura, and J

Ángel López García-Arias 4 May 19, 2022
Supervised Classification from Text (P)

MSc-Thesis Module: Masters Research Thesis Language: Python Grade: 75 Title: An investigation of supervised classification of therapeutic process from

Matthew Laws 1 Nov 22, 2021