You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
pytorch-image-models/training_hparam_examples/index.html

1571 lines
38 KiB

<!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>