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
Pun Detection and Location

Pun Detection and Location “The Boating Store Had Its Best Sail Ever”: Pronunciation-attentive Contextualized Pun Recognition Yichao Zhou, Jyun-yu Jia

lawson 3 May 13, 2022
Open-sourcing the Slates Dataset for recommender systems research

FINN.no Recommender Systems Slate Dataset This repository accompany the paper "Dynamic Slate Recommendation with Gated Recurrent Units and Thompson Sa

FINN.no 48 Nov 28, 2022
Code for Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding

🍐 quince Code for Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding 🍐 Installation $ git clone

Andrew Jesson 19 Jun 23, 2022
Pca-on-genotypes - Mini bioinformatics project - PCA on genotypes

Mini bioinformatics project: PCA on genotypes This repo contains the code from t

Maria Nattestad 8 Dec 04, 2022
Real-Time-Student-Attendence-System - Real Time Student Attendence System

Real-Time-Student-Attendence-System The Student Attendance Management System Pro

Rounak Das 1 Feb 15, 2022
Artificial Intelligence playing minesweeper 🤖

AI playing Minesweeper ✨ Minesweeper is a single-player puzzle video game. The objective of the game is to clear a rectangular board containing hidden

Vaibhaw 8 Oct 17, 2022
A repository with exploration into using transformers to predict DNA ↔ transcription factor binding

Transcription Factor binding predictions with Attention and Transformers A repository with exploration into using transformers to predict DNA ↔ transc

Phil Wang 62 Dec 20, 2022
FactSeg: Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery (TGRS)

FactSeg: Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery by Ailong Ma, Junjue Wang*, Yanfei Zhon

Kingdrone 43 Jan 05, 2023
[SIGMETRICS 2022] One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search

One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search paper | website One Proxy Device Is Enough for Hardware-Aware Neural Architec

10 Dec 16, 2022
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
A simple image/video to Desmos graph converter run locally

Desmos Bezier Renderer A simple image/video to Desmos graph converter run locally Sample Result Setup Install dependencies apt update apt install git

Kevin JY Cui 339 Dec 23, 2022
Semantic Segmentation with SegFormer on Drone Dataset.

SegFormer_Segmentation Semantic Segmentation with SegFormer on Drone Dataset. You can check out the blog on Medium You can also try out the model with

Praneet 8 Oct 20, 2022
Diabet Feature Engineering - Predict whether people have diabetes when their characteristics are specified

Diabet Feature Engineering - Predict whether people have diabetes when their characteristics are specified

Şebnem 6 Jan 18, 2022
Deeper insights into graph convolutional networks for semi-supervised learning

deeper_insights_into_GCNs Deeper insights into graph convolutional networks for semi-supervised learning References data and utils.py come from Implem

Davidham3 17 Dec 16, 2022
Kaggle Lyft Motion Prediction for Autonomous Vehicles 4th place solution

Lyft Motion Prediction for Autonomous Vehicles Code for the 4th place solution of Lyft Motion Prediction for Autonomous Vehicles on Kaggle. Discussion

44 Jun 27, 2022
Lunar is a neural network aimbot that uses real-time object detection accelerated with CUDA on Nvidia GPUs.

Lunar Lunar is a neural network aimbot that uses real-time object detection accelerated with CUDA on Nvidia GPUs. About Lunar can be modified to work

Zeyad Mansour 276 Jan 07, 2023
Efficient Two-Step Networks for Temporal Action Segmentation (Neurocomputing 2021)

Efficient Two-Step Networks for Temporal Action Segmentation This repository provides a PyTorch implementation of the paper Efficient Two-Step Network

8 Apr 16, 2022
Denoising Diffusion Probabilistic Models

Denoising Diffusion Probabilistic Models This repo contains code for DDPM training. Based on Denoising Diffusion Probabilistic Models, Improved Denois

Alexander Markov 7 Dec 15, 2022
A new benchmark for Icon Question Answering (IconQA) and a large-scale icon dataset Icon645.

IconQA About IconQA is a new diverse abstract visual question answering dataset that highlights the importance of abstract diagram understanding and c

Pan Lu 24 Dec 30, 2022