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
Deep Learning ❤️ OneFlow

Deep Learning with OneFlow made easy 🚀 ! Carefree? carefree-learn aims to provide CAREFREE usages for both users and developers. User Side Computer V

21 Oct 27, 2022
Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)

Large-Scale Long-Tailed Recognition in an Open World [Project] [Paper] [Blog] Overview Open Long-Tailed Recognition (OLTR) is the author's re-implemen

Zhongqi Miao 761 Dec 26, 2022
Code of TIP2021 Paper《SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition》. We provide both MxNet and Pytorch versions.

SFace Code of TIP2021 Paper 《SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition》. We provide both MxNet, PyTorch and Jittor versi

Zhong Yaoyao 47 Nov 25, 2022
Cross-lingual Transfer for Speech Processing using Acoustic Language Similarity

Cross-lingual Transfer for Speech Processing using Acoustic Language Similarity Indic TTS Samples can be found at https://peter-yh-wu.github.io/cross-

Peter Wu 1 Nov 12, 2022
FairyTailor: Multimodal Generative Framework for Storytelling

FairyTailor: Multimodal Generative Framework for Storytelling

Eden Bens 172 Dec 30, 2022
Learning Optical Flow from a Few Matches (CVPR 2021)

Learning Optical Flow from a Few Matches This repository contains the source code for our paper: Learning Optical Flow from a Few Matches CVPR 2021 Sh

Shihao Jiang (Zac) 159 Dec 16, 2022
Model serving at scale

Run inference at scale Cortex is an open source platform for large-scale machine learning inference workloads. Workloads Realtime APIs - respond to pr

Cortex Labs 7.9k Jan 06, 2023
🏅 Top 5% in 제2회 연구개발특구 인공지능 경진대회 AI SPARK 챌린지

AI_SPARK_CHALLENG_Object_Detection 제2회 연구개발특구 인공지능 경진대회 AI SPARK 챌린지 🏅 Top 5% in mAP(0.75) (443명 중 13등, mAP: 0.98116) 대회 설명 Edge 환경에서의 가축 Object Dete

3 Sep 19, 2022
The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training

[ICLR 2022] The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training The Unreasonable Effectiveness of

VITA 44 Dec 23, 2022
a reimplementation of Optical Flow Estimation using a Spatial Pyramid Network in PyTorch

pytorch-spynet This is a personal reimplementation of SPyNet [1] using PyTorch. Should you be making use of this work, please cite the paper according

Simon Niklaus 269 Jan 02, 2023
NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.

#NeuralTalk Warning: Deprecated. Hi there, this code is now quite old and inefficient, and now deprecated. I am leaving it on Github for educational p

Andrej 5.3k Jan 07, 2023
We are More than Our JOints: Predicting How 3D Bodies Move

We are More than Our JOints: Predicting How 3D Bodies Move Citation This repo contains the official implementation of our paper MOJO: @inproceedings{Z

72 Oct 20, 2022
ChatBot-Pytorch - A GPT-2 ChatBot implemented using Pytorch and Huggingface-transformers

ChatBot-Pytorch A GPT-2 ChatBot implemented using Pytorch and Huggingface-transf

ParZival 42 Dec 09, 2022
Official PyTorch implementation of "Evolving Search Space for Neural Architecture Search"

Evolving Search Space for Neural Architecture Search Usage Install all required dependencies in requirements.txt and replace all ..path/..to in the co

Yuanzheng Ci 10 Oct 24, 2022
Code of the paper "Shaping Visual Representations with Attributes for Few-Shot Learning (ASL)".

Shaping Visual Representations with Attributes for Few-Shot Learning This code implements the Shaping Visual Representations with Attributes for Few-S

chx_nju 9 Sep 01, 2022
Background-Click Supervision for Temporal Action Localization

Background-Click Supervision for Temporal Action Localization This repository is the official implementation of BackTAL. In this work, we study the te

LeYang 221 Oct 09, 2022
Commonsense Ability Tests

CATS Commonsense Ability Tests Dataset and script for paper Evaluating Commonsense in Pre-trained Language Models Use making_sense.py to run the exper

XUHUI ZHOU 28 Oct 19, 2022
Code for the ICML 2021 paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

ViLT Code for the paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision" Install pip install -r requirements.txt pip

Wonjae Kim 922 Jan 01, 2023
[ICML 2021, Long Talk] Delving into Deep Imbalanced Regression

Delving into Deep Imbalanced Regression This repository contains the implementation code for paper: Delving into Deep Imbalanced Regression Yuzhe Yang

Yuzhe Yang 568 Dec 30, 2022
Deep Learning segmentation suite designed for 2D microscopy image segmentation

Deep Learning segmentation suite dessigned for 2D microscopy image segmentation This repository provides researchers with a code to try different enco

7 Nov 03, 2022