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.
591 lines
24 KiB
591 lines
24 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="shortcut icon" href="../assets/images/favicon.png">
|
|
<meta name="generator" content="mkdocs-1.1.2, mkdocs-material-5.4.0">
|
|
|
|
|
|
|
|
<title>Training Examples - Pytorch Image Models</title>
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../assets/stylesheets/main.fe0cca5b.min.css">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<link href="https://fonts.gstatic.com" rel="preconnect" crossorigin>
|
|
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,400,400i,700%7CRoboto+Mono&display=fallback">
|
|
<style>body,input{font-family:"Roboto",-apple-system,BlinkMacSystemFont,Helvetica,Arial,sans-serif}code,kbd,pre{font-family:"Roboto Mono",SFMono-Regular,Consolas,Menlo,monospace}</style>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</head>
|
|
|
|
|
|
<body dir="ltr">
|
|
|
|
|
|
<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-nav md-grid" aria-label="Header">
|
|
<a href=".." title="Pytorch Image Models" class="md-header-nav__button md-logo" aria-label="Pytorch Image Models">
|
|
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 003-3 3 3 0 00-3-3 3 3 0 00-3 3 3 3 0 003 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-nav__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-nav__title" data-md-component="header-title">
|
|
|
|
<div class="md-header-nav__ellipsis">
|
|
<span class="md-header-nav__topic md-ellipsis">
|
|
Pytorch Image Models
|
|
</span>
|
|
<span class="md-header-nav__topic md-ellipsis">
|
|
|
|
Training Examples
|
|
|
|
</span>
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<label class="md-header-nav__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 0116 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 0 019.5 16 6.5 6.5 0 013 9.5 6.5 6.5 0 019.5 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" data-md-state="active">
|
|
<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 0116 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 0 019.5 16 6.5 6.5 0 013 9.5 6.5 6.5 0 019.5 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>
|
|
<button type="reset" class="md-search__icon md-icon" aria-label="Clear" data-md-component="search-reset" tabindex="-1">
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41L17.59 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>
|
|
</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-nav__source">
|
|
|
|
<a href="https://github.com/rwightman/pytorch-image-models/" title="Go to repository" class="md-source">
|
|
<div class="md-source__icon md-icon">
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><path d="M439.55 236.05L244 40.45a28.87 28.87 0 00-40.81 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 01-48.55 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 0 000 40.81l195.61 195.6a28.86 28.86 0 0040.8 0l194.69-194.69a28.86 28.86 0 000-40.81z"/></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="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">
|
|
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 003-3 3 3 0 00-3-3 3 3 0 00-3 3 3 3 0 003 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">
|
|
<div class="md-source__icon md-icon">
|
|
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><path d="M439.55 236.05L244 40.45a28.87 28.87 0 00-40.81 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 01-48.55 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 0 000 40.81l195.61 195.6a28.86 28.86 0 0040.8 0l194.69-194.69a28.86 28.86 0 000-40.81z"/></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=".." title="Getting Started" class="md-nav__link">
|
|
Getting Started
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../models/" title="Model Architectures" class="md-nav__link">
|
|
Model Architectures
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../results/" title="Results" class="md-nav__link">
|
|
Results
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../scripts/" title="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">
|
|
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 9h14V7H3v2m0 4h14v-2H3v2m0 4h14v-2H3v2m16 0h2v-2h-2v2m0-10v2h2V7h-2m0 6h2v-2h-2v2z"/></svg>
|
|
</span>
|
|
</label>
|
|
|
|
<a href="./" title="Training Examples" 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">
|
|
<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>
|
|
</span>
|
|
Table of contents
|
|
</label>
|
|
<ul class="md-nav__list" 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/" title="Feature Extraction" class="md-nav__link">
|
|
Feature Extraction
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../changes/" title="Recent Changes" class="md-nav__link">
|
|
Recent Changes
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../archived_changes/" title="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="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">
|
|
<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>
|
|
</span>
|
|
Table of contents
|
|
</label>
|
|
<ul class="md-nav__list" 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">
|
|
<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-connect 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-connect 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-connect 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-connect 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-connect 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">
|
|
|
|
<div class="md-footer-nav">
|
|
<nav class="md-footer-nav__inner md-grid" aria-label="Footer">
|
|
|
|
<a href="../scripts/" title="Scripts" class="md-footer-nav__link md-footer-nav__link--prev" rel="prev">
|
|
<div class="md-footer-nav__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-nav__title">
|
|
<div class="md-ellipsis">
|
|
<span class="md-footer-nav__direction">
|
|
Previous
|
|
</span>
|
|
Scripts
|
|
</div>
|
|
</div>
|
|
</a>
|
|
|
|
|
|
<a href="../feature_extraction/" title="Feature Extraction" class="md-footer-nav__link md-footer-nav__link--next" rel="next">
|
|
<div class="md-footer-nav__title">
|
|
<div class="md-ellipsis">
|
|
<span class="md-footer-nav__direction">
|
|
Next
|
|
</span>
|
|
Feature Extraction
|
|
</div>
|
|
</div>
|
|
<div class="md-footer-nav__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>
|
|
|
|
<div class="md-footer-meta md-typeset">
|
|
<div class="md-footer-meta__inner md-grid">
|
|
<div class="md-footer-copyright">
|
|
|
|
Made with
|
|
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
|
|
Material for MkDocs
|
|
</a>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
</footer>
|
|
|
|
</div>
|
|
|
|
<script src="../assets/javascripts/vendor.d710d30a.min.js"></script>
|
|
<script src="../assets/javascripts/bundle.b39636ac.min.js"></script><script id="__lang" type="application/json">{"clipboard.copy": "Copy to clipboard", "clipboard.copied": "Copied to clipboard", "search.config.lang": "en", "search.config.pipeline": "trimmer, stopWordFilter", "search.config.separator": "[\\s\\-]+", "search.result.placeholder": "Type to start searching", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents"}</script>
|
|
|
|
<script>
|
|
app = initialize({
|
|
base: "..",
|
|
features: [],
|
|
search: Object.assign({
|
|
worker: "../assets/javascripts/worker/search.a68abb33.min.js"
|
|
}, typeof search !== "undefined" && search)
|
|
})
|
|
</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> |