<!doctype html>
< html lang = "en" class = "no-js" >
< head >
< meta charset = "utf-8" >
< meta name = "viewport" content = "width=device-width,initial-scale=1" >
< meta name = "description" content = "Pretained Image Recognition Models" >
< link rel = "icon" href = "../assets/images/favicon.png" >
< meta name = "generator" content = "mkdocs-1.3.0, mkdocs-material-8.2.9" >
< title > Training Examples - Pytorch Image Models< / title >
< link rel = "stylesheet" href = "../assets/stylesheets/main.120efc48.min.css" >
< link rel = "stylesheet" href = "../assets/stylesheets/palette.9647289d.min.css" >
< link rel = "preconnect" href = "https://fonts.gstatic.com" crossorigin >
< link rel = "stylesheet" href = "https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback" >
< style > : root { --md-text-font : "Roboto" ; --md-code-font : "Roboto Mono" } < / style >
< script > _ _md _scope = new URL ( ".." , location ) , _ _md _get = ( e , _ = localStorage , t = _ _md _scope ) => JSON . parse ( _ . getItem ( t . pathname + "." + e ) ) , _ _md _set = ( e , _ , t = localStorage , a = _ _md _scope ) => { try { t . setItem ( a . pathname + "." + e , JSON . stringify ( _ ) ) } catch ( e ) { } } < / script >
< / head >
< body dir = "ltr" data-md-color-scheme = "" data-md-color-primary = "none" data-md-color-accent = "none" >
< input class = "md-toggle" data-md-toggle = "drawer" type = "checkbox" id = "__drawer" autocomplete = "off" >
< input class = "md-toggle" data-md-toggle = "search" type = "checkbox" id = "__search" autocomplete = "off" >
< label class = "md-overlay" for = "__drawer" > < / label >
< div data-md-component = "skip" >
< a href = "#training-examples" class = "md-skip" >
Skip to content
< / a >
< / div >
< div data-md-component = "announce" >
< / div >
< header class = "md-header" data-md-component = "header" >
< nav class = "md-header__inner md-grid" aria-label = "Header" >
< a href = ".." title = "Pytorch Image Models" class = "md-header__button md-logo" aria-label = "Pytorch Image Models" data-md-component = "logo" >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 24 24" > < path d = "M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54Z" / > < / svg >
< / a >
< label class = "md-header__button md-icon" for = "__drawer" >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 24 24" > < path d = "M3 6h18v2H3V6m0 5h18v2H3v-2m0 5h18v2H3v-2Z" / > < / svg >
< / label >
< div class = "md-header__title" data-md-component = "header-title" >
< div class = "md-header__ellipsis" >
< div class = "md-header__topic" >
< span class = "md-ellipsis" >
Pytorch Image Models
< / span >
< / div >
< div class = "md-header__topic" data-md-component = "header-topic" >
< span class = "md-ellipsis" >
Training Examples
< / span >
< / div >
< / div >
< / div >
< label class = "md-header__button md-icon" for = "__search" >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 24 24" > < path d = "M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z" / > < / svg >
< / label >
< div class = "md-search" data-md-component = "search" role = "dialog" >
< label class = "md-search__overlay" for = "__search" > < / label >
< div class = "md-search__inner" role = "search" >
< form class = "md-search__form" name = "search" >
< input type = "text" class = "md-search__input" name = "query" aria-label = "Search" placeholder = "Search" autocapitalize = "off" autocorrect = "off" autocomplete = "off" spellcheck = "false" data-md-component = "search-query" required >
< label class = "md-search__icon md-icon" for = "__search" >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 24 24" > < path d = "M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z" / > < / svg >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 24 24" > < path d = "M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12Z" / > < / svg >
< / label >
< nav class = "md-search__options" aria-label = "Search" >
< button type = "reset" class = "md-search__icon md-icon" aria-label = "Clear" tabindex = "-1" >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 24 24" > < path d = "M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41Z" / > < / svg >
< / button >
< / nav >
< / form >
< div class = "md-search__output" >
< div class = "md-search__scrollwrap" data-md-scrollfix >
< div class = "md-search-result" data-md-component = "search-result" >
< div class = "md-search-result__meta" >
Initializing search
< / div >
< ol class = "md-search-result__list" > < / ol >
< / div >
< / div >
< / div >
< / div >
< / div >
< div class = "md-header__source" >
< a href = "https://github.com/rwightman/pytorch-image-models" title = "Go to repository" class = "md-source" data-md-component = "source" >
< div class = "md-source__icon md-icon" >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 448 512" > <!-- ! Font Awesome Free 6.1.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2022 Fonticons, Inc. --> < path d = "M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z" / > < / svg >
< / div >
< div class = "md-source__repository" >
rwightman/pytorch-image-models
< / div >
< / a >
< / div >
< / nav >
< / header >
< div class = "md-container" data-md-component = "container" >
< main class = "md-main" data-md-component = "main" >
< div class = "md-main__inner md-grid" >
< div class = "md-sidebar md-sidebar--primary" data-md-component = "sidebar" data-md-type = "navigation" >
< div class = "md-sidebar__scrollwrap" >
< div class = "md-sidebar__inner" >
< nav class = "md-nav md-nav--primary" aria-label = "Navigation" data-md-level = "0" >
< label class = "md-nav__title" for = "__drawer" >
< a href = ".." title = "Pytorch Image Models" class = "md-nav__button md-logo" aria-label = "Pytorch Image Models" data-md-component = "logo" >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 24 24" > < path d = "M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54Z" / > < / svg >
< / a >
Pytorch Image Models
< / label >
< div class = "md-nav__source" >
< a href = "https://github.com/rwightman/pytorch-image-models" title = "Go to repository" class = "md-source" data-md-component = "source" >
< div class = "md-source__icon md-icon" >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 448 512" > <!-- ! Font Awesome Free 6.1.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2022 Fonticons, Inc. --> < path d = "M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z" / > < / svg >
< / div >
< div class = "md-source__repository" >
rwightman/pytorch-image-models
< / div >
< / a >
< / div >
< ul class = "md-nav__list" data-md-scrollfix >
< li class = "md-nav__item" >
< a href = ".." class = "md-nav__link" >
Getting Started
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/" class = "md-nav__link" >
Model Summaries
< / a >
< / li >
< li class = "md-nav__item md-nav__item--nested" >
< input class = "md-nav__toggle md-toggle" data-md-toggle = "__nav_3" type = "checkbox" id = "__nav_3" >
< label class = "md-nav__link" for = "__nav_3" >
Model Pages
< span class = "md-nav__icon md-icon" > < / span >
< / label >
< nav class = "md-nav" aria-label = "Model Pages" data-md-level = "1" >
< label class = "md-nav__title" for = "__nav_3" >
< span class = "md-nav__icon md-icon" > < / span >
Model Pages
< / label >
< ul class = "md-nav__list" data-md-scrollfix >
< li class = "md-nav__item" >
< a href = "../models/adversarial-inception-v3/" class = "md-nav__link" >
Adversarial Inception v3
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/advprop/" class = "md-nav__link" >
AdvProp (EfficientNet)
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/big-transfer/" class = "md-nav__link" >
Big Transfer (BiT)
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/csp-darknet/" class = "md-nav__link" >
CSP-DarkNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/csp-resnet/" class = "md-nav__link" >
CSP-ResNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/csp-resnext/" class = "md-nav__link" >
CSP-ResNeXt
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/densenet/" class = "md-nav__link" >
DenseNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/dla/" class = "md-nav__link" >
Deep Layer Aggregation
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/dpn/" class = "md-nav__link" >
Dual Path Network (DPN)
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/ecaresnet/" class = "md-nav__link" >
ECA-ResNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/efficientnet-pruned/" class = "md-nav__link" >
EfficientNet (Knapsack Pruned)
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/efficientnet/" class = "md-nav__link" >
EfficientNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/ensemble-adversarial/" class = "md-nav__link" >
Ensemble Adversarial Inception ResNet v2
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/ese-vovnet/" class = "md-nav__link" >
ESE-VoVNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/fbnet/" class = "md-nav__link" >
FBNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/gloun-inception-v3/" class = "md-nav__link" >
(Gluon) Inception v3
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/gloun-resnet/" class = "md-nav__link" >
(Gluon) ResNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/gloun-resnext/" class = "md-nav__link" >
(Gluon) ResNeXt
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/gloun-senet/" class = "md-nav__link" >
(Gluon) SENet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/gloun-seresnext/" class = "md-nav__link" >
(Gluon) SE-ResNeXt
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/gloun-xception/" class = "md-nav__link" >
(Gluon) Xception
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/hrnet/" class = "md-nav__link" >
HRNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/ig-resnext/" class = "md-nav__link" >
Instagram ResNeXt WSL
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/inception-resnet-v2/" class = "md-nav__link" >
Inception ResNet v2
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/inception-v3/" class = "md-nav__link" >
Inception v3
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/inception-v4/" class = "md-nav__link" >
Inception v4
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/legacy-se-resnet/" class = "md-nav__link" >
(Legacy) SE-ResNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/legacy-se-resnext/" class = "md-nav__link" >
(Legacy) SE-ResNeXt
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/legacy-senet/" class = "md-nav__link" >
(Legacy) SENet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/mixnet/" class = "md-nav__link" >
MixNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/mnasnet/" class = "md-nav__link" >
MnasNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/mobilenet-v2/" class = "md-nav__link" >
MobileNet v2
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/mobilenet-v3/" class = "md-nav__link" >
MobileNet v3
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/nasnet/" class = "md-nav__link" >
NASNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/noisy-student/" class = "md-nav__link" >
Noisy Student (EfficientNet)
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/pnasnet/" class = "md-nav__link" >
PNASNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/regnetx/" class = "md-nav__link" >
RegNetX
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/regnety/" class = "md-nav__link" >
RegNetY
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/res2net/" class = "md-nav__link" >
Res2Net
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/res2next/" class = "md-nav__link" >
Res2NeXt
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/resnest/" class = "md-nav__link" >
ResNeSt
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/resnet-d/" class = "md-nav__link" >
ResNet-D
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/resnet/" class = "md-nav__link" >
ResNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/resnext/" class = "md-nav__link" >
ResNeXt
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/rexnet/" class = "md-nav__link" >
RexNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/se-resnet/" class = "md-nav__link" >
SE-ResNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/selecsls/" class = "md-nav__link" >
SelecSLS
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/seresnext/" class = "md-nav__link" >
SE-ResNeXt
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/skresnet/" class = "md-nav__link" >
SK-ResNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/skresnext/" class = "md-nav__link" >
SK-ResNeXt
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/spnasnet/" class = "md-nav__link" >
SPNASNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/ssl-resnet/" class = "md-nav__link" >
SSL ResNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/ssl-resnext/" class = "md-nav__link" >
SSL ResNeXT
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/swsl-resnet/" class = "md-nav__link" >
SWSL ResNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/swsl-resnext/" class = "md-nav__link" >
SWSL ResNeXt
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/tf-efficientnet-condconv/" class = "md-nav__link" >
(Tensorflow) EfficientNet CondConv
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/tf-efficientnet-lite/" class = "md-nav__link" >
(Tensorflow) EfficientNet Lite
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/tf-efficientnet/" class = "md-nav__link" >
(Tensorflow) EfficientNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/tf-inception-v3/" class = "md-nav__link" >
(Tensorflow) Inception v3
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/tf-mixnet/" class = "md-nav__link" >
(Tensorflow) MixNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/tf-mobilenet-v3/" class = "md-nav__link" >
(Tensorflow) MobileNet v3
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/tresnet/" class = "md-nav__link" >
TResNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/vision-transformer/" class = "md-nav__link" >
Vision Transformer (ViT)
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/wide-resnet/" class = "md-nav__link" >
Wide ResNet
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../models/xception/" class = "md-nav__link" >
Xception
< / a >
< / li >
< / ul >
< / nav >
< / li >
< li class = "md-nav__item" >
< a href = "../results/" class = "md-nav__link" >
Results
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../scripts/" class = "md-nav__link" >
Scripts
< / a >
< / li >
< li class = "md-nav__item md-nav__item--active" >
< input class = "md-nav__toggle md-toggle" data-md-toggle = "toc" type = "checkbox" id = "__toc" >
< label class = "md-nav__link md-nav__link--active" for = "__toc" >
Training Examples
< span class = "md-nav__icon md-icon" > < / span >
< / label >
< a href = "./" class = "md-nav__link md-nav__link--active" >
Training Examples
< / a >
< nav class = "md-nav md-nav--secondary" aria-label = "Table of contents" >
< label class = "md-nav__title" for = "__toc" >
< span class = "md-nav__icon md-icon" > < / span >
Table of contents
< / label >
< ul class = "md-nav__list" data-md-component = "toc" data-md-scrollfix >
< li class = "md-nav__item" >
< a href = "#efficientnet-b2-with-randaugment-804-top-1-951-top-5" class = "md-nav__link" >
EfficientNet-B2 with RandAugment - 80.4 top-1, 95.1 top-5
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#mixnet-xl-with-randaugment-805-top-1-949-top-5" class = "md-nav__link" >
MixNet-XL with RandAugment - 80.5 top-1, 94.9 top-5
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#se-resnext-26-d-and-se-resnext-26-t" class = "md-nav__link" >
SE-ResNeXt-26-D and SE-ResNeXt-26-T
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#efficientnet-b3-with-randaugment-815-top-1-957-top-5" class = "md-nav__link" >
EfficientNet-B3 with RandAugment - 81.5 top-1, 95.7 top-5
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#efficientnet-b0-with-randaugment-777-top-1-953-top-5" class = "md-nav__link" >
EfficientNet-B0 with RandAugment - 77.7 top-1, 95.3 top-5
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#resnet50-with-jsd-loss-and-randaugment-clean-2x-ra-augs-7904-top-1-9439-top-5" class = "md-nav__link" >
ResNet50 with JSD loss and RandAugment (clean + 2x RA augs) - 79.04 top-1, 94.39 top-5
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#efficientnet-es-edgetpu-small-with-randaugment-78066-top-1-93926-top-5" class = "md-nav__link" >
EfficientNet-ES (EdgeTPU-Small) with RandAugment - 78.066 top-1, 93.926 top-5
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#mobilenetv3-large-100-75766-top-1-92542-top-5" class = "md-nav__link" >
MobileNetV3-Large-100 - 75.766 top-1, 92,542 top-5
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#resnext-50-32x4d-w-randaugment-79762-top-1-9460-top-5" class = "md-nav__link" >
ResNeXt-50 32x4d w/ RandAugment - 79.762 top-1, 94.60 top-5
< / a >
< / li >
< / ul >
< / nav >
< / li >
< li class = "md-nav__item" >
< a href = "../feature_extraction/" class = "md-nav__link" >
Feature Extraction
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../changes/" class = "md-nav__link" >
Recent Changes
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "../archived_changes/" class = "md-nav__link" >
Archived Changes
< / a >
< / li >
< / ul >
< / nav >
< / div >
< / div >
< / div >
< div class = "md-sidebar md-sidebar--secondary" data-md-component = "sidebar" data-md-type = "toc" >
< div class = "md-sidebar__scrollwrap" >
< div class = "md-sidebar__inner" >
< nav class = "md-nav md-nav--secondary" aria-label = "Table of contents" >
< label class = "md-nav__title" for = "__toc" >
< span class = "md-nav__icon md-icon" > < / span >
Table of contents
< / label >
< ul class = "md-nav__list" data-md-component = "toc" data-md-scrollfix >
< li class = "md-nav__item" >
< a href = "#efficientnet-b2-with-randaugment-804-top-1-951-top-5" class = "md-nav__link" >
EfficientNet-B2 with RandAugment - 80.4 top-1, 95.1 top-5
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#mixnet-xl-with-randaugment-805-top-1-949-top-5" class = "md-nav__link" >
MixNet-XL with RandAugment - 80.5 top-1, 94.9 top-5
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#se-resnext-26-d-and-se-resnext-26-t" class = "md-nav__link" >
SE-ResNeXt-26-D and SE-ResNeXt-26-T
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#efficientnet-b3-with-randaugment-815-top-1-957-top-5" class = "md-nav__link" >
EfficientNet-B3 with RandAugment - 81.5 top-1, 95.7 top-5
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#efficientnet-b0-with-randaugment-777-top-1-953-top-5" class = "md-nav__link" >
EfficientNet-B0 with RandAugment - 77.7 top-1, 95.3 top-5
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#resnet50-with-jsd-loss-and-randaugment-clean-2x-ra-augs-7904-top-1-9439-top-5" class = "md-nav__link" >
ResNet50 with JSD loss and RandAugment (clean + 2x RA augs) - 79.04 top-1, 94.39 top-5
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#efficientnet-es-edgetpu-small-with-randaugment-78066-top-1-93926-top-5" class = "md-nav__link" >
EfficientNet-ES (EdgeTPU-Small) with RandAugment - 78.066 top-1, 93.926 top-5
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#mobilenetv3-large-100-75766-top-1-92542-top-5" class = "md-nav__link" >
MobileNetV3-Large-100 - 75.766 top-1, 92,542 top-5
< / a >
< / li >
< li class = "md-nav__item" >
< a href = "#resnext-50-32x4d-w-randaugment-79762-top-1-9460-top-5" class = "md-nav__link" >
ResNeXt-50 32x4d w/ RandAugment - 79.762 top-1, 94.60 top-5
< / a >
< / li >
< / ul >
< / nav >
< / div >
< / div >
< / div >
< div class = "md-content" data-md-component = "content" >
< article class = "md-content__inner md-typeset" >
< a href = "https://github.com/rwightman/pytorch-image-models/edit/master/docs/training_hparam_examples.md" title = "Edit this page" class = "md-content__button md-icon" >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 24 24" > < path d = "M20.71 7.04c.39-.39.39-1.04 0-1.41l-2.34-2.34c-.37-.39-1.02-.39-1.41 0l-1.84 1.83 3.75 3.75M3 17.25V21h3.75L17.81 9.93l-3.75-3.75L3 17.25Z" / > < / svg >
< / a >
< h1 id = "training-examples" > Training Examples< / h1 >
< h2 id = "efficientnet-b2-with-randaugment-804-top-1-951-top-5" > EfficientNet-B2 with RandAugment - 80.4 top-1, 95.1 top-5< / h2 >
< p > These params are for dual Titan RTX cards with NVIDIA Apex installed:< / p >
< p > < code > ./distributed_train.sh 2 /imagenet/ --model efficientnet_b2 -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.3 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .016< / code > < / p >
< h2 id = "mixnet-xl-with-randaugment-805-top-1-949-top-5" > MixNet-XL with RandAugment - 80.5 top-1, 94.9 top-5< / h2 >
< p > This params are for dual Titan RTX cards with NVIDIA Apex installed:< / p >
< p > < code > ./distributed_train.sh 2 /imagenet/ --model mixnet_xl -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .969 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.3 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.3 --amp --lr .016 --dist-bn reduce< / code > < / p >
< h2 id = "se-resnext-26-d-and-se-resnext-26-t" > SE-ResNeXt-26-D and SE-ResNeXt-26-T< / h2 >
< p > These hparams (or similar) work well for a wide range of ResNet architecture, generally a good idea to increase the epoch # as the model size increases... ie approx 180-200 for ResNe(X)t50, and 220+ for larger. Increase batch size and LR proportionally for better GPUs or with AMP enabled. These params were for 2 1080Ti cards:< / p >
< p > < code > ./distributed_train.sh 2 /imagenet/ --model seresnext26t_32x4d --lr 0.1 --warmup-epochs 5 --epochs 160 --weight-decay 1e-4 --sched cosine --reprob 0.4 --remode pixel -b 112< / code > < / p >
< h2 id = "efficientnet-b3-with-randaugment-815-top-1-957-top-5" > EfficientNet-B3 with RandAugment - 81.5 top-1, 95.7 top-5< / h2 >
< p > The training of this model started with the same command line as EfficientNet-B2 w/ RA above. After almost three weeks of training the process crashed. The results weren't looking amazing so I resumed the training several times with tweaks to a few params (increase RE prob, decrease rand-aug, increase ema-decay). Nothing looked great. I ended up averaging the best checkpoints from all restarts. The result is mediocre at default res/crop but oddly performs much better with a full image test crop of 1.0. < / p >
< h2 id = "efficientnet-b0-with-randaugment-777-top-1-953-top-5" > EfficientNet-B0 with RandAugment - 77.7 top-1, 95.3 top-5< / h2 >
< p > < a href = "https://github.com/michaelklachko" > Michael Klachko< / a > achieved these results with the command line for B2 adapted for larger batch size, with the recommended B0 dropout rate of 0.2.< / p >
< p > < code > ./distributed_train.sh 2 /imagenet/ --model efficientnet_b0 -b 384 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .048< / code > < / p >
< h2 id = "resnet50-with-jsd-loss-and-randaugment-clean-2x-ra-augs-7904-top-1-9439-top-5" > ResNet50 with JSD loss and RandAugment (clean + 2x RA augs) - 79.04 top-1, 94.39 top-5< / h2 >
< p > Trained on two older 1080Ti cards, this took a while. Only slightly, non statistically better ImageNet validation result than my first good AugMix training of 78.99. However, these weights are more robust on tests with ImageNetV2, ImageNet-Sketch, etc. Unlike my first AugMix runs, I've enabled SplitBatchNorm, disabled random erasing on the clean split, and cranked up random erasing prob on the 2 augmented paths.< / p >
< p > < code > ./distributed_train.sh 2 /imagenet -b 64 --model resnet50 --sched cosine --epochs 200 --lr 0.05 --amp --remode pixel --reprob 0.6 --aug-splits 3 --aa rand-m9-mstd0.5-inc1 --resplit --split-bn --jsd --dist-bn reduce< / code > < / p >
< h2 id = "efficientnet-es-edgetpu-small-with-randaugment-78066-top-1-93926-top-5" > EfficientNet-ES (EdgeTPU-Small) with RandAugment - 78.066 top-1, 93.926 top-5< / h2 >
< p > Trained by < a href = "https://github.com/andravin" > Andrew Lavin< / a > with 8 V100 cards. Model EMA was not used, final checkpoint is the average of 8 best checkpoints during training.< / p >
< p > < code > ./distributed_train.sh 8 /imagenet --model efficientnet_es -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .064< / code > < / p >
< h2 id = "mobilenetv3-large-100-75766-top-1-92542-top-5" > MobileNetV3-Large-100 - 75.766 top-1, 92,542 top-5< / h2 >
< p > < code > ./distributed_train.sh 2 /imagenet/ --model mobilenetv3_large_100 -b 512 --sched step --epochs 600 --decay-epochs 2.4 --decay-rate .973 --opt rmsproptf --opt-eps .001 -j 7 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .064 --lr-noise 0.42 0.9< / code > < / p >
< h2 id = "resnext-50-32x4d-w-randaugment-79762-top-1-9460-top-5" > ResNeXt-50 32x4d w/ RandAugment - 79.762 top-1, 94.60 top-5< / h2 >
< p > These params will also work well for SE-ResNeXt-50 and SK-ResNeXt-50 and likely 101. I used them for the SK-ResNeXt-50 32x4d that I trained with 2 GPU using a slightly higher LR per effective batch size (lr=0.18, b=192 per GPU). The cmd line below are tuned for 8 GPU training.< / p >
< p > < code > ./distributed_train.sh 8 /imagenet --model resnext50_32x4d --lr 0.6 --warmup-epochs 5 --epochs 240 --weight-decay 1e-4 --sched cosine --reprob 0.4 --recount 3 --remode pixel --aa rand-m7-mstd0.5-inc1 -b 192 -j 6 --amp --dist-bn reduce< / code > < / p >
< / article >
< / div >
< / div >
< / main >
< footer class = "md-footer" >
< nav class = "md-footer__inner md-grid" aria-label = "Footer" >
< a href = "../scripts/" class = "md-footer__link md-footer__link--prev" aria-label = "Previous: Scripts" rel = "prev" >
< div class = "md-footer__button md-icon" >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 24 24" > < path d = "M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12Z" / > < / svg >
< / div >
< div class = "md-footer__title" >
< div class = "md-ellipsis" >
< span class = "md-footer__direction" >
Previous
< / span >
Scripts
< / div >
< / div >
< / a >
< a href = "../feature_extraction/" class = "md-footer__link md-footer__link--next" aria-label = "Next: Feature Extraction" rel = "next" >
< div class = "md-footer__title" >
< div class = "md-ellipsis" >
< span class = "md-footer__direction" >
Next
< / span >
Feature Extraction
< / div >
< / div >
< div class = "md-footer__button md-icon" >
< svg xmlns = "http://www.w3.org/2000/svg" viewBox = "0 0 24 24" > < path d = "M4 11v2h12l-5.5 5.5 1.42 1.42L19.84 12l-7.92-7.92L10.5 5.5 16 11H4Z" / > < / svg >
< / div >
< / a >
< / nav >
< div class = "md-footer-meta md-typeset" >
< div class = "md-footer-meta__inner md-grid" >
< div class = "md-copyright" >
Made with
< a href = "https://squidfunk.github.io/mkdocs-material/" target = "_blank" rel = "noopener" >
Material for MkDocs
< / a >
< / div >
< / div >
< / div >
< / footer >
< / div >
< div class = "md-dialog" data-md-component = "dialog" >
< div class = "md-dialog__inner md-typeset" > < / div >
< / div >
< script id = "__config" type = "application/json" > { "base" : ".." , "features" : [ ] , "search" : "../assets/javascripts/workers/search.2a1c317c.min.js" , "translations" : { "clipboard.copied" : "Copied to clipboard" , "clipboard.copy" : "Copy to clipboard" , "search.config.lang" : "en" , "search.config.pipeline" : "trimmer, stopWordFilter" , "search.config.separator" : "[\\s\\-]+" , "search.placeholder" : "Search" , "search.result.more.one" : "1 more on this page" , "search.result.more.other" : "# more on this page" , "search.result.none" : "No matching documents" , "search.result.one" : "1 matching document" , "search.result.other" : "# matching documents" , "search.result.placeholder" : "Type to start searching" , "search.result.term.missing" : "Missing" , "select.version.title" : "Select version" } } < / script >
< script src = "../assets/javascripts/bundle.6e54b5cd.min.js" > < / script >
< script src = "https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-MML-AM_CHTML" > < / script >
< script src = "https://cdnjs.cloudflare.com/ajax/libs/tablesort/5.2.1/tablesort.min.js" > < / script >
< script src = "../javascripts/tables.js" > < / script >
< / body >
< / html >
