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
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

Apache MXNet (incubating) for Deep Learning Master Docs License Apache MXNet (incubating) is a deep learning framework designed for both efficiency an

ROCm Software Platform 29 Nov 16, 2022
chen2020iros: Learning an Overlap-based Observation Model for 3D LiDAR Localization.

Overlap-based 3D LiDAR Monte Carlo Localization This repo contains the code for our IROS2020 paper: Learning an Overlap-based Observation Model for 3D

Photogrammetry & Robotics Bonn 219 Dec 15, 2022
TensorFlow implementation of original paper : https://github.com/hszhao/PSPNet

Keras implementation of PSPNet(caffe) Implemented Architecture of Pyramid Scene Parsing Network in Keras. For the best compability please use Python3.

VladKry 386 Dec 29, 2022
EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation

EFENet EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation Code is a bit messy now. I woud clean up soon. For training the EF

Yaping Zhao 19 Nov 05, 2022
Project code for weakly supervised 3D object detectors using wide-baseline multi-view traffic camera data: WIBAM.

WIBAM (Work in progress) Weakly Supervised Training of Monocular 3D Object Detectors Using Wide Baseline Multi-view Traffic Camera Data 3D object dete

Matthew Howe 10 Aug 24, 2022
Attentive Implicit Representation Networks (AIR-Nets)

Attentive Implicit Representation Networks (AIR-Nets) Preprint | Supplementary | Accepted at the International Conference on 3D Vision (3DV) teaser.mo

29 Dec 07, 2022
Official pytorch implementation of "DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion"

DSPoint Official implementation of "DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion". Paper link: https://arxiv.org/abs/2111.10

Ziyao Zeng 14 Feb 26, 2022
Impelmentation for paper Feature Generation and Hypothesis Verification for Reliable Face Anti-Spoofing

FGHV Impelmentation for paper Feature Generation and Hypothesis Verification for Reliable Face Anti-Spoofing Requirements Python 3.6 Pytorch 1.5.0 Cud

5 Jun 02, 2022
Localized representation learning from Vision and Text (LoVT)

Localized Vision-Text Pre-Training Contrastive learning has proven effective for pre- training image models on unlabeled data and achieved great resul

Philip Müller 10 Dec 07, 2022
Implements pytorch code for the Accelerated SGD algorithm.

AccSGD This is the code associated with Accelerated SGD algorithm used in the paper On the insufficiency of existing momentum schemes for Stochastic O

205 Jan 02, 2023
Main Results on ImageNet with Pretrained Models

This repository contains Pytorch evaluation code, training code and pretrained models for the following projects: SPACH (A Battle of Network Structure

Microsoft 151 Dec 14, 2022
Applicator Kit for Modo allow you to apply Apple ARKit Face Tracking data from your iPhone or iPad to your characters in Modo.

Applicator Kit for Modo Applicator Kit for Modo allow you to apply Apple ARKit Face Tracking data from your iPhone or iPad with a TrueDepth camera to

Andrew Buttigieg 3 Aug 24, 2021
DETReg: Unsupervised Pretraining with Region Priors for Object Detection

DETReg: Unsupervised Pretraining with Region Priors for Object Detection Amir Bar, Xin Wang, Vadim Kantorov, Colorado J Reed, Roei Herzig, Gal Chechik

Amir Bar 283 Dec 27, 2022
MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data

This repository is the official PyTorch implementation of Meta-Balance. Find the paper on arxiv MetaBalance: High-Performance Neural Networks for Clas

Arpit Bansal 20 Oct 18, 2021
[ICCV21] Self-Calibrating Neural Radiance Fields

Self-Calibrating Neural Radiance Fields, ICCV, 2021 Project Page | Paper | Video Author Information Yoonwoo Jeong [Google Scholar] Seokjun Ahn [Google

381 Dec 30, 2022
Romanian Automatic Speech Recognition from the ROBIN project

RobinASR This repository contains Robin's Automatic Speech Recognition (RobinASR) for the Romanian language based on the DeepSpeech2 architecture, tog

RACAI 10 Jan 01, 2023
Builds a LoRa radio frequency fingerprint identification (RFFI) system based on deep learning techiniques

This project builds a LoRa radio frequency fingerprint identification (RFFI) system based on deep learning techiniques.

20 Dec 30, 2022
Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization

Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization Official PyTorch implementation for our URST (Ultra-Resolution Sty

czczup 148 Dec 27, 2022
An implementation of Fastformer: Additive Attention Can Be All You Need in TensorFlow

Fast Transformer This repo implements Fastformer: Additive Attention Can Be All You Need by Wu et al. in TensorFlow. Fast Transformer is a Transformer

Rishit Dagli 139 Dec 28, 2022
An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)

AlphaZero-Gomoku This is an implementation of the AlphaZero algorithm for playing the simple board game Gomoku (also called Gobang or Five in a Row) f

Junxiao Song 2.8k Dec 26, 2022