Migrations
/
pytorch-image-models
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
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.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'ef9970fd4d'
${ noResults }
pytorch-image-models/models/tf-efficientnet-condconv/index.html

1558 lines
43 KiB
Raw Blame History

<!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-1.1.2, mkdocs-material-7.0.6">
<title>(Tensorflow) EfficientNet CondConv - Pytorch Image Models</title>
<link rel="stylesheet" href="../../assets/stylesheets/main.2c0c5eaf.min.css">
<link rel="stylesheet" href="../../assets/stylesheets/palette.7fa14f5b.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,400,400i,700%7CRoboto+Mono&display=fallback">
<style>:root{--md-text-font-family:"Roboto";--md-code-font-family:"Roboto Mono"}</style>
</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="#tensorflow-efficientnet-condconv" 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">
(Tensorflow) EfficientNet CondConv
</span>
</div>
</div>
</div>
<div class="md-header__options">
</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" data-md-state="active" 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>
<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 6.41L17.59 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__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"><path d="M439.55 236.05L244 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"><path d="M439.55 236.05L244 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="../" class="md-nav__link">
Model Architectures
</a>
</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">
<a href="../../training_hparam_examples/" class="md-nav__link">
Training Examples
</a>
</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>
<li class="md-nav__item md-nav__item--active md-nav__item--nested">
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_9" type="checkbox" id="__nav_9" checked>
<label class="md-nav__link" for="__nav_9">
Models
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" aria-label="Models" data-md-level="1">
<label class="md-nav__title" for="__nav_9">
<span class="md-nav__icon md-icon"></span>
Models
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../adversarial-inception-v3/" class="md-nav__link">
Adversarial Inception v3
</a>
</li>
<li class="md-nav__item">
<a href="../advprop/" class="md-nav__link">
AdvProp (EfficientNet)
</a>
</li>
<li class="md-nav__item">
<a href="../big-transfer/" class="md-nav__link">
Big Transfer (BiT)
</a>
</li>
<li class="md-nav__item">
<a href="../csp-darknet/" class="md-nav__link">
CSP-DarkNet
</a>
</li>
<li class="md-nav__item">
<a href="../csp-resnet/" class="md-nav__link">
CSP-ResNet
</a>
</li>
<li class="md-nav__item">
<a href="../csp-resnext/" class="md-nav__link">
CSP-ResNeXt
</a>
</li>
<li class="md-nav__item">
<a href="../densenet/" class="md-nav__link">
DenseNet
</a>
</li>
<li class="md-nav__item">
<a href="../dla/" class="md-nav__link">
Deep Layer Aggregation
</a>
</li>
<li class="md-nav__item">
<a href="../dpn/" class="md-nav__link">
Dual Path Network (DPN)
</a>
</li>
<li class="md-nav__item">
<a href="../ecaresnet/" class="md-nav__link">
ECA-ResNet
</a>
</li>
<li class="md-nav__item">
<a href="../efficientnet-pruned/" class="md-nav__link">
EfficientNet (Knapsack Pruned)
</a>
</li>
<li class="md-nav__item">
<a href="../efficientnet/" class="md-nav__link">
EfficientNet
</a>
</li>
<li class="md-nav__item">
<a href="../ensemble-adversarial/" class="md-nav__link">
Ensemble Adversarial Inception ResNet v2
</a>
</li>
<li class="md-nav__item">
<a href="../ese-vovnet/" class="md-nav__link">
ESE-VoVNet
</a>
</li>
<li class="md-nav__item">
<a href="../fbnet/" class="md-nav__link">
FBNet
</a>
</li>
<li class="md-nav__item">
<a href="../gloun-inception-v3/" class="md-nav__link">
(Gluon) Inception v3
</a>
</li>
<li class="md-nav__item">
<a href="../gloun-resnet/" class="md-nav__link">
(Gluon) ResNet
</a>
</li>
<li class="md-nav__item">
<a href="../gloun-resnext/" class="md-nav__link">
(Gluon) ResNeXt
</a>
</li>
<li class="md-nav__item">
<a href="../gloun-senet/" class="md-nav__link">
(Gluon) SENet
</a>
</li>
<li class="md-nav__item">
<a href="../gloun-seresnext/" class="md-nav__link">
(Gluon) SE-ResNeXt
</a>
</li>
<li class="md-nav__item">
<a href="../gloun-xception/" class="md-nav__link">
(Gluon) Xception
</a>
</li>
<li class="md-nav__item">
<a href="../hrnet/" class="md-nav__link">
HRNet
</a>
</li>
<li class="md-nav__item">
<a href="../ig-resnext/" class="md-nav__link">
Instagram ResNeXt WSL
</a>
</li>
<li class="md-nav__item">
<a href="../inception-resnet-v2/" class="md-nav__link">
Inception ResNet v2
</a>
</li>
<li class="md-nav__item">
<a href="../inception-v3/" class="md-nav__link">
Inception v3
</a>
</li>
<li class="md-nav__item">
<a href="../inception-v4/" class="md-nav__link">
Inception v4
</a>
</li>
<li class="md-nav__item">
<a href="../legacy-se-resnet/" class="md-nav__link">
(Legacy) SE-ResNet
</a>
</li>
<li class="md-nav__item">
<a href="../legacy-se-resnext/" class="md-nav__link">
(Legacy) SE-ResNeXt
</a>
</li>
<li class="md-nav__item">
<a href="../legacy-senet/" class="md-nav__link">
(Legacy) SENet
</a>
</li>
<li class="md-nav__item">
<a href="../mixnet/" class="md-nav__link">
MixNet
</a>
</li>
<li class="md-nav__item">
<a href="../mnasnet/" class="md-nav__link">
MnasNet
</a>
</li>
<li class="md-nav__item">
<a href="../mobilenet-v2/" class="md-nav__link">
MobileNet v2
</a>
</li>
<li class="md-nav__item">
<a href="../mobilenet-v3/" class="md-nav__link">
MobileNet v3
</a>
</li>
<li class="md-nav__item">
<a href="../nasnet/" class="md-nav__link">
NASNet
</a>
</li>
<li class="md-nav__item">
<a href="../noisy-student/" class="md-nav__link">
Noisy Student (EfficientNet)
</a>
</li>
<li class="md-nav__item">
<a href="../pnasnet/" class="md-nav__link">
PNASNet
</a>
</li>
<li class="md-nav__item">
<a href="../regnetx/" class="md-nav__link">
RegNetX
</a>
</li>
<li class="md-nav__item">
<a href="../regnety/" class="md-nav__link">
RegNetY
</a>
</li>
<li class="md-nav__item">
<a href="../res2net/" class="md-nav__link">
Res2Net
</a>
</li>
<li class="md-nav__item">
<a href="../res2next/" class="md-nav__link">
Res2NeXt
</a>
</li>
<li class="md-nav__item">
<a href="../resnest/" class="md-nav__link">
ResNeSt
</a>
</li>
<li class="md-nav__item">
<a href="../resnet-d/" class="md-nav__link">
ResNet-D
</a>
</li>
<li class="md-nav__item">
<a href="../resnet/" class="md-nav__link">
ResNet
</a>
</li>
<li class="md-nav__item">
<a href="../resnext/" class="md-nav__link">
ResNeXt
</a>
</li>
<li class="md-nav__item">
<a href="../rexnet/" class="md-nav__link">
RexNet
</a>
</li>
<li class="md-nav__item">
<a href="../se-resnet/" class="md-nav__link">
SE-ResNet
</a>
</li>
<li class="md-nav__item">
<a href="../selecsls/" class="md-nav__link">
SelecSLS
</a>
</li>
<li class="md-nav__item">
<a href="../seresnext/" class="md-nav__link">
SE-ResNeXt
</a>
</li>
<li class="md-nav__item">
<a href="../skresnet/" class="md-nav__link">
SK-ResNet
</a>
</li>
<li class="md-nav__item">
<a href="../skresnext/" class="md-nav__link">
SK-ResNeXt
</a>
</li>
<li class="md-nav__item">
<a href="../spnasnet/" class="md-nav__link">
SPNASNet
</a>
</li>
<li class="md-nav__item">
<a href="../ssl-resnet/" class="md-nav__link">
SSL ResNet
</a>
</li>
<li class="md-nav__item">
<a href="../ssl-resnext/" class="md-nav__link">
SSL ResNeXT
</a>
</li>
<li class="md-nav__item">
<a href="../swsl-resnet/" class="md-nav__link">
SWSL ResNet
</a>
</li>
<li class="md-nav__item">
<a href="../swsl-resnext/" class="md-nav__link">
SWSL ResNeXt
</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">
(Tensorflow) EfficientNet CondConv
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
(Tensorflow) EfficientNet CondConv
</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="#how-do-i-use-this-model-on-an-image" class="md-nav__link">
How do I use this model on an image?
</a>
</li>
<li class="md-nav__item">
<a href="#how-do-i-finetune-this-model" class="md-nav__link">
How do I finetune this model?
</a>
</li>
<li class="md-nav__item">
<a href="#how-do-i-train-this-model" class="md-nav__link">
How do I train this model?
</a>
</li>
<li class="md-nav__item">
<a href="#citation" class="md-nav__link">
Citation
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../tf-efficientnet-lite/" class="md-nav__link">
(Tensorflow) EfficientNet Lite
</a>
</li>
<li class="md-nav__item">
<a href="../tf-efficientnet/" class="md-nav__link">
(Tensorflow) EfficientNet
</a>
</li>
<li class="md-nav__item">
<a href="../tf-inception-v3/" class="md-nav__link">
(Tensorflow) Inception v3
</a>
</li>
<li class="md-nav__item">
<a href="../tf-mixnet/" class="md-nav__link">
(Tensorflow) MixNet
</a>
</li>
<li class="md-nav__item">
<a href="../tf-mobilenet-v3/" class="md-nav__link">
(Tensorflow) MobileNet v3
</a>
</li>
<li class="md-nav__item">
<a href="../tresnet/" class="md-nav__link">
TResNet
</a>
</li>
<li class="md-nav__item">
<a href="../vision-transformer/" class="md-nav__link">
Vision Transformer (ViT)
</a>
</li>
<li class="md-nav__item">
<a href="../wide-resnet/" class="md-nav__link">
Wide ResNet
</a>
</li>
<li class="md-nav__item">
<a href="../xception/" class="md-nav__link">
Xception
</a>
</li>
</ul>
</nav>
</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="#how-do-i-use-this-model-on-an-image" class="md-nav__link">
How do I use this model on an image?
</a>
</li>
<li class="md-nav__item">
<a href="#how-do-i-finetune-this-model" class="md-nav__link">
How do I finetune this model?
</a>
</li>
<li class="md-nav__item">
<a href="#how-do-i-train-this-model" class="md-nav__link">
How do I train this model?
</a>
</li>
<li class="md-nav__item">
<a href="#citation" class="md-nav__link">
Citation
</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/models/tf-efficientnet-condconv.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="tensorflow-efficientnet-condconv">(Tensorflow) EfficientNet CondConv</h1>
<p><strong>EfficientNet</strong> is a convolutional neural network architecture and scaling method that uniformly scales all dimensions of depth/width/resolution using a <em>compound coefficient</em>. Unlike conventional practice that arbitrary scales these factors, the EfficientNet scaling method uniformly scales network width, depth, and resolution with a set of fixed scaling coefficients. For example, if we want to use <span><span class="MathJax_Preview">2^N</span><script type="math/tex">2^N</script></span> times more computational resources, then we can simply increase the network depth by <span><span class="MathJax_Preview">\alpha ^ N</span><script type="math/tex">\alpha ^ N</script></span>, width by <span><span class="MathJax_Preview">\beta ^ N</span><script type="math/tex">\beta ^ N</script></span>, and image size by <span><span class="MathJax_Preview">\gamma ^ N</span><script type="math/tex">\gamma ^ N</script></span>, where <span><span class="MathJax_Preview">\alpha, \beta, \gamma</span><script type="math/tex">\alpha, \beta, \gamma</script></span> are constant coefficients determined by a small grid search on the original small model. EfficientNet uses a compound coefficient <span><span class="MathJax_Preview">\phi</span><script type="math/tex">\phi</script></span> to uniformly scales network width, depth, and resolution in a principled way.</p>
<p>The compound scaling method is justified by the intuition that if the input image is bigger, then the network needs more layers to increase the receptive field and more channels to capture more fine-grained patterns on the bigger image.</p>
<p>The base EfficientNet-B0 network is based on the inverted bottleneck residual blocks of <a href="https://paperswithcode.com/method/mobilenetv2">MobileNetV2</a>, in addition to squeeze-and-excitation blocks.</p>
<p>This collection of models amends EfficientNet by adding <a href="https://paperswithcode.com/method/condconv">CondConv</a> convolutions.</p>
<p>The weights from this model were ported from <a href="https://github.com/tensorflow/tpu">Tensorflow/TPU</a>.</p>
<h2 id="how-do-i-use-this-model-on-an-image">How do I use this model on an image?</h2>
<p>To load a pretrained model:</p>
<div class="highlight"><pre><span></span><code><span class="kn">import</span> <span class="nn">timm</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">timm</span><span class="o">.</span><span class="n">create_model</span><span class="p">(</span><span class="s1">&#39;tf_efficientnet_cc_b0_4e&#39;</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">model</span><span class="o">.</span><span class="n">eval</span><span class="p">()</span>
</code></pre></div>
<p>To load and preprocess the image:
<div class="highlight"><pre><span></span><code><span class="kn">import</span> <span class="nn">urllib</span>
<span class="kn">from</span> <span class="nn">PIL</span> <span class="kn">import</span> <span class="n">Image</span>
<span class="kn">from</span> <span class="nn">timm.data</span> <span class="kn">import</span> <span class="n">resolve_data_config</span>
<span class="kn">from</span> <span class="nn">timm.data.transforms_factory</span> <span class="kn">import</span> <span class="n">create_transform</span>
<span class="n">config</span> <span class="o">=</span> <span class="n">resolve_data_config</span><span class="p">({},</span> <span class="n">model</span><span class="o">=</span><span class="n">model</span><span class="p">)</span>
<span class="n">transform</span> <span class="o">=</span> <span class="n">create_transform</span><span class="p">(</span><span class="o">**</span><span class="n">config</span><span class="p">)</span>
<span class="n">url</span><span class="p">,</span> <span class="n">filename</span> <span class="o">=</span> <span class="p">(</span><span class="s2">&quot;https://github.com/pytorch/hub/raw/master/images/dog.jpg&quot;</span><span class="p">,</span> <span class="s2">&quot;dog.jpg&quot;</span><span class="p">)</span>
<span class="n">urllib</span><span class="o">.</span><span class="n">request</span><span class="o">.</span><span class="n">urlretrieve</span><span class="p">(</span><span class="n">url</span><span class="p">,</span> <span class="n">filename</span><span class="p">)</span>
<span class="n">img</span> <span class="o">=</span> <span class="n">Image</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">filename</span><span class="p">)</span><span class="o">.</span><span class="n">convert</span><span class="p">(</span><span class="s1">&#39;RGB&#39;</span><span class="p">)</span>
<span class="n">tensor</span> <span class="o">=</span> <span class="n">transform</span><span class="p">(</span><span class="n">img</span><span class="p">)</span><span class="o">.</span><span class="n">unsqueeze</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span> <span class="c1"># transform and add batch dimension</span>
</code></pre></div></p>
<p>To get the model predictions:
<div class="highlight"><pre><span></span><code><span class="kn">import</span> <span class="nn">torch</span>
<span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">():</span>
<span class="n">out</span> <span class="o">=</span> <span class="n">model</span><span class="p">(</span><span class="n">tensor</span><span class="p">)</span>
<span class="n">probabilities</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">functional</span><span class="o">.</span><span class="n">softmax</span><span class="p">(</span><span class="n">out</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">dim</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="n">probabilities</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
<span class="c1"># prints: torch.Size([1000])</span>
</code></pre></div></p>
<p>To get the top-5 predictions class names:
<div class="highlight"><pre><span></span><code><span class="c1"># Get imagenet class mappings</span>
<span class="n">url</span><span class="p">,</span> <span class="n">filename</span> <span class="o">=</span> <span class="p">(</span><span class="s2">&quot;https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt&quot;</span><span class="p">,</span> <span class="s2">&quot;imagenet_classes.txt&quot;</span><span class="p">)</span>
<span class="n">urllib</span><span class="o">.</span><span class="n">request</span><span class="o">.</span><span class="n">urlretrieve</span><span class="p">(</span><span class="n">url</span><span class="p">,</span> <span class="n">filename</span><span class="p">)</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s2">&quot;imagenet_classes.txt&quot;</span><span class="p">,</span> <span class="s2">&quot;r&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">categories</span> <span class="o">=</span> <span class="p">[</span><span class="n">s</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="n">f</span><span class="o">.</span><span class="n">readlines</span><span class="p">()]</span>
<span class="c1"># Print top categories per image</span>
<span class="n">top5_prob</span><span class="p">,</span> <span class="n">top5_catid</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">topk</span><span class="p">(</span><span class="n">probabilities</span><span class="p">,</span> <span class="mi">5</span><span class="p">)</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">top5_prob</span><span class="o">.</span><span class="n">size</span><span class="p">(</span><span class="mi">0</span><span class="p">)):</span>
<span class="nb">print</span><span class="p">(</span><span class="n">categories</span><span class="p">[</span><span class="n">top5_catid</span><span class="p">[</span><span class="n">i</span><span class="p">]],</span> <span class="n">top5_prob</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">item</span><span class="p">())</span>
<span class="c1"># prints class names and probabilities like:</span>
<span class="c1"># [(&#39;Samoyed&#39;, 0.6425196528434753), (&#39;Pomeranian&#39;, 0.04062102362513542), (&#39;keeshond&#39;, 0.03186424449086189), (&#39;white wolf&#39;, 0.01739676296710968), (&#39;Eskimo dog&#39;, 0.011717947199940681)]</span>
</code></pre></div></p>
<p>Replace the model name with the variant you want to use, e.g. <code>tf_efficientnet_cc_b0_4e</code>. You can find the IDs in the model summaries at the top of this page.</p>
<p>To extract image features with this model, follow the <a href="https://rwightman.github.io/pytorch-image-models/feature_extraction/">timm feature extraction examples</a>, just change the name of the model you want to use.</p>
<h2 id="how-do-i-finetune-this-model">How do I finetune this model?</h2>
<p>You can finetune any of the pre-trained models just by changing the classifier (the last layer).
<div class="highlight"><pre><span></span><code><span class="n">model</span> <span class="o">=</span> <span class="n">timm</span><span class="o">.</span><span class="n">create_model</span><span class="p">(</span><span class="s1">&#39;tf_efficientnet_cc_b0_4e&#39;</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">num_classes</span><span class="o">=</span><span class="n">NUM_FINETUNE_CLASSES</span><span class="p">)</span>
</code></pre></div>
To finetune on your own dataset, you have to write a training loop or adapt <a href="https://github.com/rwightman/pytorch-image-models/blob/master/train.py">timm's training
script</a> to use your dataset.</p>
<h2 id="how-do-i-train-this-model">How do I train this model?</h2>
<p>You can follow the <a href="https://rwightman.github.io/pytorch-image-models/scripts/">timm recipe scripts</a> for training a new model afresh.</p>
<h2 id="citation">Citation</h2>
<div class="highlight"><pre><span></span><code><span class="nc">@article</span><span class="p">{</span><span class="nl">DBLP:journals/corr/abs-1904-04971</span><span class="p">,</span>
<span class="na">author</span> <span class="p">=</span> <span class="s">{Brandon Yang and</span>
<span class="s"> Gabriel Bender and</span>
<span class="s"> Quoc V. Le and</span>
<span class="s"> Jiquan Ngiam}</span><span class="p">,</span>
<span class="na">title</span> <span class="p">=</span> <span class="s">{Soft Conditional Computation}</span><span class="p">,</span>
<span class="na">journal</span> <span class="p">=</span> <span class="s">{CoRR}</span><span class="p">,</span>
<span class="na">volume</span> <span class="p">=</span> <span class="s">{abs/1904.04971}</span><span class="p">,</span>
<span class="na">year</span> <span class="p">=</span> <span class="s">{2019}</span><span class="p">,</span>
<span class="na">url</span> <span class="p">=</span> <span class="s">{http://arxiv.org/abs/1904.04971}</span><span class="p">,</span>
<span class="na">archivePrefix</span> <span class="p">=</span> <span class="s">{arXiv}</span><span class="p">,</span>
<span class="na">eprint</span> <span class="p">=</span> <span class="s">{1904.04971}</span><span class="p">,</span>
<span class="na">timestamp</span> <span class="p">=</span> <span class="s">{Thu, 25 Apr 2019 13:55:01 +0200}</span><span class="p">,</span>
<span class="na">biburl</span> <span class="p">=</span> <span class="s">{https://dblp.org/rec/journals/corr/abs-1904-04971.bib}</span><span class="p">,</span>
<span class="na">bibsource</span> <span class="p">=</span> <span class="s">{dblp computer science bibliography, https://dblp.org}</span>
<span class="p">}</span>
</code></pre></div>
<!--
Type: model-index
Collections:
- Name: TF EfficientNet CondConv
Paper:
Title: 'CondConv: Conditionally Parameterized Convolutions for Efficient Inference'
URL: https://paperswithcode.com/paper/soft-conditional-computation
Models:
- Name: tf_efficientnet_cc_b0_4e
In Collection: TF EfficientNet CondConv
Metadata:
FLOPs: 224153788
Parameters: 13310000
File Size: 53490940
Architecture:
- 1x1 Convolution
- Average Pooling
- Batch Normalization
- CondConv
- Convolution
- Dense Connections
- Dropout
- Inverted Residual Block
- Squeeze-and-Excitation Block
- Swish
Tasks:
- Image Classification
Training Techniques:
- AutoAugment
- Label Smoothing
- RMSProp
- Stochastic Depth
- Weight Decay
Training Data:
- ImageNet
ID: tf_efficientnet_cc_b0_4e
LR: 0.256
Epochs: 350
Crop Pct: '0.875'
Momentum: 0.9
Batch Size: 2048
Image Size: '224'
Weight Decay: 1.0e-05
Interpolation: bicubic
RMSProp Decay: 0.9
Label Smoothing: 0.1
BatchNorm Momentum: 0.99
Code: https://github.com/rwightman/pytorch-image-models/blob/9a25fdf3ad0414b4d66da443fe60ae0aa14edc84/timm/models/efficientnet.py#L1561
Weights: https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/tf_efficientnet_cc_b0_4e-4362b6b2.pth
Results:
- Task: Image Classification
Dataset: ImageNet
Metrics:
Top 1 Accuracy: 77.32%
Top 5 Accuracy: 93.32%
- Name: tf_efficientnet_cc_b0_8e
In Collection: TF EfficientNet CondConv
Metadata:
FLOPs: 224158524
Parameters: 24010000
File Size: 96287616
Architecture:
- 1x1 Convolution
- Average Pooling
- Batch Normalization
- CondConv
- Convolution
- Dense Connections
- Dropout
- Inverted Residual Block
- Squeeze-and-Excitation Block
- Swish
Tasks:
- Image Classification
Training Techniques:
- AutoAugment
- Label Smoothing
- RMSProp
- Stochastic Depth
- Weight Decay
Training Data:
- ImageNet
ID: tf_efficientnet_cc_b0_8e
LR: 0.256
Epochs: 350
Crop Pct: '0.875'
Momentum: 0.9
Batch Size: 2048
Image Size: '224'
Weight Decay: 1.0e-05
Interpolation: bicubic
RMSProp Decay: 0.9
Label Smoothing: 0.1
BatchNorm Momentum: 0.99
Code: https://github.com/rwightman/pytorch-image-models/blob/9a25fdf3ad0414b4d66da443fe60ae0aa14edc84/timm/models/efficientnet.py#L1572
Weights: https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/tf_efficientnet_cc_b0_8e-66184a25.pth
Results:
- Task: Image Classification
Dataset: ImageNet
Metrics:
Top 1 Accuracy: 77.91%
Top 5 Accuracy: 93.65%
- Name: tf_efficientnet_cc_b1_8e
In Collection: TF EfficientNet CondConv
Metadata:
FLOPs: 370427824
Parameters: 39720000
File Size: 159206198
Architecture:
- 1x1 Convolution
- Average Pooling
- Batch Normalization
- CondConv
- Convolution
- Dense Connections
- Dropout
- Inverted Residual Block
- Squeeze-and-Excitation Block
- Swish
Tasks:
- Image Classification
Training Techniques:
- AutoAugment
- Label Smoothing
- RMSProp
- Stochastic Depth
- Weight Decay
Training Data:
- ImageNet
ID: tf_efficientnet_cc_b1_8e
LR: 0.256
Epochs: 350
Crop Pct: '0.882'
Momentum: 0.9
Batch Size: 2048
Image Size: '240'
Weight Decay: 1.0e-05
Interpolation: bicubic
RMSProp Decay: 0.9
Label Smoothing: 0.1
BatchNorm Momentum: 0.99
Code: https://github.com/rwightman/pytorch-image-models/blob/9a25fdf3ad0414b4d66da443fe60ae0aa14edc84/timm/models/efficientnet.py#L1584
Weights: https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/tf_efficientnet_cc_b1_8e-f7c79ae1.pth
Results:
- Task: Image Classification
Dataset: ImageNet
Metrics:
Top 1 Accuracy: 79.33%
Top 5 Accuracy: 94.37%
-->
</article>
</div>
</div>
</main>
<footer class="md-footer">
<nav class="md-footer__inner md-grid" aria-label="Footer">
<a href="../swsl-resnext/" class="md-footer__link md-footer__link--prev" 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>
SWSL ResNeXt
</div>
</div>
</a>
<a href="../tf-efficientnet-lite/" class="md-footer__link md-footer__link--next" rel="next">
<div class="md-footer__title">
<div class="md-ellipsis">
<span class="md-footer__direction">
Next
</span>
(Tensorflow) EfficientNet Lite
</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-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>
<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": [], "translations": {"clipboard.copy": "Copy to clipboard", "clipboard.copied": "Copied to clipboard", "search.config.lang": "en", "search.config.pipeline": "trimmer, stopWordFilter", "search.config.separator": "[\\s\\-]+", "search.placeholder": "Search", "search.result.placeholder": "Type to start searching", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.term.missing": "Missing"}, "search": "../../assets/javascripts/workers/search.fb4a9340.min.js", "version": null}</script>
<script src="../../assets/javascripts/bundle.a1c7c35e.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>
Reference in new issue View Git Blame Copy Permalink