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
This is the official implementation of Elaborative Rehearsal for Zero-shot Action Recognition (ICCV2021)

Elaborative Rehearsal for Zero-shot Action Recognition This is an official implementation of: Shizhe Chen and Dong Huang, Elaborative Rehearsal for Ze

DeLightCMU 26 Sep 24, 2022
PyTorch 1.5 implementation for paper DECOR-GAN: 3D Shape Detailization by Conditional Refinement.

DECOR-GAN PyTorch 1.5 implementation for paper DECOR-GAN: 3D Shape Detailization by Conditional Refinement, Zhiqin Chen, Vladimir G. Kim, Matthew Fish

Zhiqin Chen 72 Dec 31, 2022
Colossal-AI: A Unified Deep Learning System for Large-Scale Parallel Training

ColossalAI An integrated large-scale model training system with efficient parallelization techniques. arXiv: Colossal-AI: A Unified Deep Learning Syst

HPC-AI Tech 7.9k Jan 08, 2023
Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation

Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation (CVPR2019) This is a pytorch implementatio

Yawei Luo 280 Jan 01, 2023
NeurIPS 2021 Datasets and Benchmarks Track

AP-10K: A Benchmark for Animal Pose Estimation in the Wild Introduction | Updates | Overview | Download | Training Code | Key Questions | License Intr

AP-10K 82 Dec 11, 2022
All the code and files related to the MI-Lab of UE19CS305 course in sem 5

Machine-Intelligence-Lab-CS305 The compilation of all the code an drelated files from MI-Lab UE19CS305 (of batch 2019-2023) offered by PES University

Arvind Krishna 3 Nov 10, 2022
Video Frame Interpolation with Transformer (CVPR2022)

VFIformer Official PyTorch implementation of our CVPR2022 paper Video Frame Interpolation with Transformer Dependencies python = 3.8 pytorch = 1.8.0

DV Lab 63 Dec 16, 2022
Out-of-boundary View Synthesis towards Full-frame Video Stabilization

Out-of-boundary View Synthesis towards Full-frame Video Stabilization Introduction | Update | Results Demo | Introduction This repository contains the

25 Oct 10, 2022
Hierarchical User Intent Graph Network for Multimedia Recommendation

Hierarchical User Intent Graph Network for Multimedia Recommendation This is our Pytorch implementation for the paper: Hierarchical User Intent Graph

6 Jan 05, 2023
SCU OlympicsRunning Baseline

Competition 1v1 running Environment check details in Jidi Competition RLChina2021智能体竞赛 做出的修改: 奖励重塑:修改了环境,重新设置了奖励的分配,使得奖励组成不只有零和博弈,还有探索环境的奖励。 算法微调:修改了官

ZiSeoi Wong 2 Nov 23, 2021
A Python package to process & model ChEMBL data.

insilico: A Python package to process & model ChEMBL data. ChEMBL is a manually curated chemical database of bioactive molecules with drug-like proper

Steven Newton 0 Dec 09, 2021
The repository for freeCodeCamp's YouTube course, Algorithmic Trading in Python

Algorithmic Trading in Python This repository Course Outline Section 1: Algorithmic Trading Fundamentals What is Algorithmic Trading? The Differences

Nick McCullum 1.8k Jan 02, 2023
The project page of paper: Architecture disentanglement for deep neural networks [ICCV 2021, oral]

This is the project page for the paper: Architecture Disentanglement for Deep Neural Networks, Jie Hu, Liujuan Cao, Tong Tong, Ye Qixiang, ShengChuan

Jie Hu 15 Aug 30, 2022
RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation

RIFE - Real Time Video Interpolation arXiv | YouTube | Colab | Tutorial | Demo Table of Contents Introduction Collection Usage Evaluation Training and

hzwer 3k Jan 04, 2023
​ This is the Pytorch implementation of Progressive Attentional Manifold Alignment.

PAMA This is the Pytorch implementation of Progressive Attentional Manifold Alignment. Requirements python 3.6 pytorch 1.2.0+ PIL, numpy, matplotlib C

98 Nov 15, 2022
Multi-scale discriminator feature-wise loss function

Multi-Scale Discriminative Feature Loss This repository provides code for Multi-Scale Discriminative Feature (MDF) loss for image reconstruction algor

Graphics and Displays group - University of Cambridge 76 Dec 12, 2022
Code implementation from my Medium blog post: [Transformers from Scratch in PyTorch]

transformer-from-scratch Code for my Medium blog post: Transformers from Scratch in PyTorch Note: This Transformer code does not include masked attent

Frank Odom 27 Dec 21, 2022
[ACL 2022] LinkBERT: A Knowledgeable Language Model 😎 Pretrained with Document Links

LinkBERT: A Knowledgeable Language Model Pretrained with Document Links This repo provides the model, code & data of our paper: LinkBERT: Pretraining

Michihiro Yasunaga 264 Jan 01, 2023
A Comprehensive Study on Learning-Based PE Malware Family Classification Methods

A Comprehensive Study on Learning-Based PE Malware Family Classification Methods Datasets Because of copyright issues, both the MalwareBazaar dataset

8 Oct 21, 2022
IndoNLI: A Natural Language Inference Dataset for Indonesian

IndoNLI: A Natural Language Inference Dataset for Indonesian This is a repository for data and code accompanying our EMNLP 2021 paper "IndoNLI: A Natu

15 Feb 10, 2022