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
CTC segmentation python package

CTC segmentation CTC segmentation can be used to find utterances alignments within large audio files. This repository contains the ctc-segmentation py

Ludwig Kürzinger 217 Jan 04, 2023
The official implementation of NeurIPS 2021 paper: Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks

Introduction This repository includes the source code for "Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks", which is pu

machen 11 Nov 27, 2022
Implement slightly different caffe-segnet in tensorflow

Tensorflow-SegNet Implement slightly different (see below for detail) SegNet in tensorflow, successfully trained segnet-basic in CamVid dataset. Due t

Tseng Kuan Lun 364 Oct 27, 2022
Open-source python package for the extraction of Radiomics features from 2D and 3D images and binary masks.

pyradiomics v3.0.1 Build Status Linux macOS Windows Radiomics feature extraction in Python This is an open-source python package for the extraction of

Artificial Intelligence in Medicine (AIM) Program 842 Dec 28, 2022
[ICCV'21] PlaneTR: Structure-Guided Transformers for 3D Plane Recovery

PlaneTR: Structure-Guided Transformers for 3D Plane Recovery This is the official implementation of our ICCV 2021 paper News There maybe some bugs in

73 Nov 30, 2022
Partial implementation of ODE-GAN technique from the paper Training Generative Adversarial Networks by Solving Ordinary Differential Equations

ODE GAN (Prototype) in PyTorch Partial implementation of ODE-GAN technique from the paper Training Generative Adversarial Networks by Solving Ordinary

Somshubra Majumdar 15 Feb 10, 2022
SpinalNet: Deep Neural Network with Gradual Input

SpinalNet: Deep Neural Network with Gradual Input This repository contains scripts for training different variations of the SpinalNet and its counterp

H M Dipu Kabir 142 Dec 30, 2022
PyTorch implementation of paper: AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer, ICCV 2021.

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer [Paper] [PyTorch Implementation] [Paddle Implementation] Overview This reposit

148 Dec 30, 2022
《Truly shift-invariant convolutional neural networks》(2021)

Truly shift-invariant convolutional neural networks [Paper] Authors: Anadi Chaman and Ivan Dokmanić Convolutional neural networks were always assumed

Anadi Chaman 46 Dec 19, 2022
FMA: A Dataset For Music Analysis

FMA: A Dataset For Music Analysis Michaël Defferrard, Kirell Benzi, Pierre Vandergheynst, Xavier Bresson. International Society for Music Information

Michaël Defferrard 1.8k Dec 29, 2022
Metric learning algorithms in Python

metric-learn: Metric Learning in Python metric-learn contains efficient Python implementations of several popular supervised and weakly-supervised met

1.3k Dec 28, 2022
Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging

Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging This repository contains an implementation

Computational Photography Lab @ SFU 1.1k Jan 02, 2023
This is the repository for The Machine Learning Workshops, published by AI DOJO

This is the repository for The Machine Learning Workshops, published by AI DOJO. It contains all the workshop's code with supporting project files necessary to work through the code.

AI Dojo 12 May 06, 2022
7th place solution of Human Protein Atlas - Single Cell Classification on Kaggle

kaggle-hpa-2021-7th-place-solution Code for 7th place solution of Human Protein Atlas - Single Cell Classification on Kaggle. A description of the met

8 Jul 09, 2021
A reimplementation of DCGAN in PyTorch

DCGAN in PyTorch A reimplementation of DCGAN in PyTorch. Although there is an abundant source of code and examples found online (as well as an officia

Diego Porres 6 Jan 08, 2022
This project is based on our SIGGRAPH 2021 paper, ROSEFusion: Random Optimization for Online DenSE Reconstruction under Fast Camera Motion .

ROSEFusion 🌹 This project is based on our SIGGRAPH 2021 paper, ROSEFusion: Random Optimization for Online DenSE Reconstruction under Fast Camera Moti

219 Dec 27, 2022
StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks

StackGAN Pytorch implementation Inception score evaluation StackGAN-v2-pytorch Tensorflow implementation for reproducing main results in the paper Sta

Han Zhang 1.8k Dec 21, 2022
The final project of "Applying AI to EHR Data" of "AI for Healthcare" nanodegree - Udacity.

Patient Selection for Diabetes Drug Testing Project Overview EHR data is becoming a key source of real-world evidence (RWE) for the pharmaceutical ind

Omar Laham 1 Jan 14, 2022
Code for "Neural 3D Scene Reconstruction with the Manhattan-world Assumption" CVPR 2022 Oral

News 05/10/2022 To make the comparison on ScanNet easier, we provide all quantitative and qualitative results of baselines here, including COLMAP, COL

ZJU3DV 365 Dec 30, 2022