SOTA model in CIFAR10

Overview

A PyTorch Implementation of CIFAR Tricks

调研了CIFAR10数据集上各种trick,数据增强,正则化方法,并进行了实现。目前项目告一段落,如果有更好的想法,或者希望一起维护这个项目可以提issue或者在我的主页找到我的联系方式。

0. Requirements

  • Python 3.6+
  • torch=1.8.0+cu111
  • torchvision+0.9.0+cu111
  • tqdm=4.26.0
  • PyYAML=6.0

1. Implements

1.1 Tricks

  • Warmup
  • Cosine LR Decay
  • SAM
  • Label Smooth
  • KD
  • Adabound
  • Xavier Kaiming init
  • lr finder

1.2 Augmentation

  • Auto Augmentation
  • Cutout
  • Mixup
  • RICAP
  • Random Erase
  • ShakeDrop

2. Training

2.1 CIFAR-10训练示例

WideResNet28-10 baseline on CIFAR-10:

python train.py --dataset cifar10

WideResNet28-10 +RICAP on CIFAR-10:

python train.py --dataset cifar10 --ricap True

WideResNet28-10 +Random Erasing on CIFAR-10:

python train.py --dataset cifar10 --random-erase True

WideResNet28-10 +Mixup on CIFAR-10:

python train.py --dataset cifar10 --mixup True

3. Results

3.1 原pytorch-ricap的结果

Model Error rate Loss Error rate (paper)
WideResNet28-10 baseline 3.82(96.18) 0.158 3.89
WideResNet28-10 +RICAP 2.82(97.18) 0.141 2.85
WideResNet28-10 +Random Erasing 3.18(96.82) 0.114 4.65
WideResNet28-10 +Mixup 3.02(96.98) 0.158 3.02

3.2 Reimplementation结果

Model Error rate Loss Error rate (paper)
WideResNet28-10 baseline 3.78(96.22) 3.89
WideResNet28-10 +RICAP 2.81(97.19) 2.85
WideResNet28-10 +Random Erasing 3.03(96.97) 0.113 4.65
WideResNet28-10 +Mixup 2.93(97.07) 0.158 3.02

3.3 Half data快速训练验证各网络结构

reimplementation models(no augmentation, half data,epoch200,bs128)

Model Error rate Loss
lenet(cpu爆炸) (70.76)
wideresnet 3.78(96.22)
resnet20 (89.72)
senet (92.34)
resnet18 (92.08)
resnet34 (92.48)
resnet50 (91.72)
regnet (92.58)
nasnet out of mem
shake_resnet26_2x32d (93.06)
shake_resnet26_2x64d (94.14)
densenet (92.06)
dla (92.58)
googlenet (91.90) 0.2675
efficientnetb0(利用率低且慢) (86.82) 0.5024
mobilenet(利用率低) (89.18)
mobilenetv2 (91.06)
pnasnet (90.44)
preact_resnet (90.76)
resnext (92.30)
vgg(cpugpu利用率都高) (88.38)
inceptionv3 (91.84)
inceptionv4 (91.10)
inception_resnet_v2 (83.46)
rir (92.34) 0.3932
squeezenet(CPU利用率高) (89.16) 0.4311
stochastic_depth_resnet18 (90.22)
xception
dpn (92.06) 0.3002
ge_resnext29_8x64d (93.86) 巨慢

3.4 测试cpu gpu影响

TEST: scale/kernel ToyNet

修改网络的卷积层深度,并进行训练,可以得到以下结论:

结论:lenet这种卷积量比较少,只有两层的,cpu利用率高,gpu利用率低。在这个基础上增加深度,用vgg那种直筒方式增加深度,发现深度越深,cpu利用率越低,gpu利用率越高。

修改训练过程的batch size,可以得到以下结论:

结论:bs会影响收敛效果。

3.5 StepLR优化下测试cutout和mixup

architecture epoch cutout mixup C10 test acc (%)
shake_resnet26_2x64d 200 96.33
shake_resnet26_2x64d 200 96.99
shake_resnet26_2x64d 200 96.60
shake_resnet26_2x64d 200 96.46

3.6 测试SAM,ASAM,Cosine,LabelSmooth

architecture epoch SAM ASAM Cosine LR Decay LabelSmooth C10 test acc (%)
shake_resnet26_2x64d 200 96.51
shake_resnet26_2x64d 200 96.80
shake_resnet26_2x64d 200 96.61
shake_resnet26_2x64d 200 96.57

PS:其他库在加长训练过程(epoch=1800)情况下可以实现 shake_resnet26_2x64d achieved 97.71% test accuracy with cutout and mixup!!

3.7 测试cosine lr + shake

architecture epoch cutout mixup C10 test acc (%)
shake_resnet26_2x64d 300 96.66
shake_resnet26_2x64d 300 97.21
shake_resnet26_2x64d 300 96.90
shake_resnet26_2x64d 300 96.73

1800 epoch CIFAR ZOO中结果,由于耗时过久,未进行复现。

architecture epoch cutout mixup C10 test acc (%)
shake_resnet26_2x64d 1800 96.94(cifar zoo)
shake_resnet26_2x64d 1800 97.20(cifar zoo)
shake_resnet26_2x64d 1800 97.42(cifar zoo)
shake_resnet26_2x64d 1800 97.71(cifar zoo)

3.8 Divide and Co-training方案研究

  • lr:
    • warmup (20 epoch)
    • cosine lr decay
    • lr=0.1
    • total epoch(300 epoch)
  • bs=128
  • aug:
    • Random Crop and resize
    • Random left-right flipping
    • AutoAugment
    • Normalization
    • Random Erasing
    • Mixup
  • weight decay=5e-4 (bias and bn undecayed)
  • kaiming weight init
  • optimizer: nesterov

复现:((v100:gpu1) 4min*300/60=20h) top1: 97.59% 本项目目前最高值。

python train.py --model 'pyramidnet272' \
                --name 'divide-co-train' \
                --autoaugmentation True \ 
                --random-erase True \
                --mixup True \
                --epochs 300 \
                --sched 'warmcosine' \
                --optims 'nesterov' \
                --bs 128 \
                --root '/home/dpj/project/data'

3.9 测试多种数据增强

architecture epoch cutout mixup autoaugment random-erase C10 test acc (%)
shake_resnet26_2x64d 200 96.42
shake_resnet26_2x64d 200 96.49
shake_resnet26_2x64d 200 96.17
shake_resnet26_2x64d 200 96.25
shake_resnet26_2x64d 200 96.20
shake_resnet26_2x64d 200 95.82
shake_resnet26_2x64d 200 96.02
shake_resnet26_2x64d 200 96.00
shake_resnet26_2x64d 200 95.83
shake_resnet26_2x64d 200 95.89
shake_resnet26_2x64d 200 96.25
python train.py --model 'shake_resnet26_2x64d' --name 'ss64_orgin' --bs 64
python train.py --model 'shake_resnet26_2x64d' --name 'ss64_c' --cutout True --bs 64
python train.py --model 'shake_resnet26_2x64d' --name 'ss64_m' --mixup True --bs 64
python train.py --model 'shake_resnet26_2x64d' --name 'ss64_a' --autoaugmentation True  --bs 64
python train.py --model 'shake_resnet26_2x64d' --name 'ss64_r' --random-erase True  --bs 64
python train.py --model 'shake_resnet26_2x64d' --name 'ss64_cm'  --cutout True --mixup True --bs 64
python train.py --model 'shake_resnet26_2x64d' --name 'ss64_ca' --cutout True --autoaugmentation True --bs 64
python train.py --model 'shake_resnet26_2x64d' --name 'ss64_cr' --cutout True --random-erase True --bs 64
python train.py --model 'shake_resnet26_2x64d' --name 'ss64_ma' --mixup True --autoaugmentation True --bs 64
python train.py --model 'shake_resnet26_2x64d' --name 'ss64_mr' --mixup True --random-erase True --bs 64
python train.py --model 'shake_resnet26_2x64d' --name 'ss64_ar' --autoaugmentation True --random-erase True  --bs 64

4. Reference

[1] https://github.com/BIGBALLON/CIFAR-ZOO

[2] https://github.com/pprp/MutableNAS

[3] https://github.com/clovaai/CutMix-PyTorch

[4] https://github.com/4uiiurz1/pytorch-ricap

[5] https://github.com/NUDTNASLab/pytorch-image-models

[6] https://github.com/facebookresearch/LaMCTS

[7] https://github.com/Alibaba-MIIL/ImageNet21K

Owner
PJDong
Computer vision learner, deep learner
PJDong
Implementing a simplified copy of Shazam application from scratch using MinHashing and LSH.

Building Shazam from scratch In this repository we tried to implement a simplified copy of the Shazam application able to tell you the name of a song

Arturo Ghinassi 0 Nov 17, 2022
Deep Learning Datasets Maker is a QGIS plugin to make datasets creation easier for raster and vector data.

Deep Learning Dataset Maker Deep Learning Datasets Maker is a QGIS plugin to make datasets creation easier for raster and vector data. How to use Down

deepbands 25 Dec 15, 2022
CC-GENERATOR - A python script for generating CC

CC-GENERATOR A python script for generating CC NOTE: This tool is for Educationa

Lêkzï 6 Oct 14, 2022
General neural ODE and DAE modules for power system dynamic modeling.

Py_PSNODE General neural ODE and DAE modules for power system dynamic modeling. The PyTorch-based ODE solver is developed based on torchdiffeq. Sample

14 Dec 31, 2022
Meaningful titles for tabs and PDF downloads! Also supports tab search.

arxiv-utils If you are a researcher that reads a lot on ArXiv, you'll benefit a lot from this web extension. Renames the title of PDF page to the pape

Johnson 174 Dec 20, 2022
Image Data Augmentation in Keras

Image data augmentation is a technique that can be used to artificially expand the size of a training dataset by creating modified versions of images in the dataset.

Grace Ugochi Nneji 3 Feb 15, 2022
Contains source code for the winning solution of the xView3 challenge

Winning Solution for xView3 Challenge This repository contains source code and pretrained models for my (Eugene Khvedchenya) solution to xView 3 Chall

Eugene Khvedchenya 51 Dec 30, 2022
This program creates a formatted excel file which highlights the undervalued stock according to Graham's number.

Over-and-Undervalued-Stocks Of Nepse Using Graham's Number Scrap the latest data using different websites and creates a formatted excel file that high

6 May 03, 2022
1st ranked 'driver careless behavior detection' for AI Online Competition 2021, hosted by MSIT Korea.

2021AICompetition-03 본 repo 는 mAy-I Inc. 팀으로 참가한 2021 인공지능 온라인 경진대회 중 [이미지] 운전 사고 예방을 위한 운전자 부주의 행동 검출 모델] 태스크 수행을 위한 레포지토리입니다. mAy-I 는 과학기술정보통신부가 주최하

Junhyuk Park 9 Dec 01, 2022
A Python framework for developing parallelized Computational Fluid Dynamics software to solve the hyperbolic 2D Euler equations on distributed, multi-block structured grids.

pyHype: Computational Fluid Dynamics in Python pyHype is a Python framework for developing parallelized Computational Fluid Dynamics software to solve

Mohamed Khalil 21 Nov 22, 2022
The second project in Python course on FCC

Assignment Write a function named add_time that takes in two required parameters and one optional parameter: a start time in the 12-hour clock format

Denise T 1 Dec 13, 2021
Official repository of the paper "A Variational Approximation for Analyzing the Dynamics of Panel Data". Mixed Effect Neural ODE. UAI 2021.

Official repository of the paper (UAI 2021) "A Variational Approximation for Analyzing the Dynamics of Panel Data", Mixed Effect Neural ODE. Panel dat

Jurijs Nazarovs 7 Nov 26, 2022
Keqing Chatbot With Python

KeqingChatbot A public running instance can be found on telegram as @keqingchat_bot. Requirements Python 3.8 or higher. A bot token. Local Deploy git

Rikka-Chan 2 Jan 16, 2022
Intrusion Detection System using ensemble learning (machine learning)

IDS-ML implementation of an intrusion detection system using ensemble machine learning methods Data set This project is carried out using the UNSW-15

4 Nov 25, 2022
Neural Caption Generator with Attention

Neural Caption Generator with Attention Tensorflow implementation of "Show

Taeksoo Kim 510 Nov 30, 2022
Keras implementation of AdaBound

AdaBound for Keras Keras port of AdaBound Optimizer for PyTorch, from the paper Adaptive Gradient Methods with Dynamic Bound of Learning Rate. Usage A

Somshubra Majumdar 132 Sep 23, 2022
Loopy belief propagation for factor graphs on discrete variables, in JAX!

PGMax implements general factor graphs for discrete probabilistic graphical models (PGMs), and hardware-accelerated differentiable loopy belief propagation (LBP) in JAX.

Vicarious 62 Dec 23, 2022
Notebook and code to synthesize complex and highly dimensional datasets using Gretel APIs.

Gretel Trainer This code is designed to help users successfully train synthetic models on complex datasets with high row and column counts. The code w

Gretel.ai 24 Nov 03, 2022
Much faster than SORT(Simple Online and Realtime Tracking), a little worse than SORT

QSORT QSORT(Quick + Simple Online and Realtime Tracking) is a simple online and realtime tracking algorithm for 2D multiple object tracking in video s

Yonghye Kwon 8 Jul 27, 2022
A GPT, made only of MLPs, in Jax

MLP GPT - Jax (wip) A GPT, made only of MLPs, in Jax. The specific MLP to be used are gMLPs with the Spatial Gating Units. Working Pytorch implementat

Phil Wang 53 Sep 27, 2022