<!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 > CSP-DarkNet - 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 = "#csp-darknet" 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" >
CSP-DarkNet
< / 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 Summaries
< / 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_3" type = "checkbox" id = "__nav_3" checked >
< 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 = "../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 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" >
CSP-DarkNet
< span class = "md-nav__icon md-icon" > < / span >
< / label >
< a href = "./" class = "md-nav__link md-nav__link--active" >
CSP-DarkNet
< / 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 = "../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" >
< a href = "../tf-efficientnet-condconv/" class = "md-nav__link" >
(Tensorflow) EfficientNet CondConv
< / a >
< / 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 >
< 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 >
< / 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/csp-darknet.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 = "csp-darknet" > CSP-DarkNet< / h1 >
< p > < strong > CSPDarknet53< / strong > is a convolutional neural network and backbone for object detection that uses < a href = "https://paperswithcode.com/method/darknet-53" > DarkNet-53< / a > . It employs a CSPNet strategy to partition the feature map of the base layer into two parts and then merges them through a cross-stage hierarchy. The use of a split and merge strategy allows for more gradient flow through the network. < / p >
< p > This CNN is used as the backbone for < a href = "https://paperswithcode.com/method/yolov4" > YOLOv4< / 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" > ' cspdarknet53' < / 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" > " https://github.com/pytorch/hub/raw/master/images/dog.jpg" < / span > < span class = "p" > ,< / span > < span class = "s2" > " dog.jpg" < / 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" > ' RGB' < / 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" > " https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt" < / span > < span class = "p" > ,< / span > < span class = "s2" > " imagenet_classes.txt" < / 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" > " imagenet_classes.txt" < / span > < span class = "p" > ,< / span > < span class = "s2" > " r" < / 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" > # [(' Samoyed' , 0.6425196528434753), (' Pomeranian' , 0.04062102362513542), (' keeshond' , 0.03186424449086189), (' white wolf' , 0.01739676296710968), (' Eskimo dog' , 0.011717947199940681)]< / span >
< / code > < / pre > < / div > < / p >
< p > Replace the model name with the variant you want to use, e.g. < code > cspdarknet53< / 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" > ' cspdarknet53' < / 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" > @misc< / span > < span class = "p" > {< / span > < span class = "nl" > bochkovskiy2020yolov4< / span > < span class = "p" > ,< / span >
< span class = "na" > title< / span > < span class = "p" > =< / span > < span class = "s" > {YOLOv4: Optimal Speed and Accuracy of Object Detection}< / span > < span class = "p" > ,< / span >
< span class = "na" > author< / span > < span class = "p" > =< / span > < span class = "s" > {Alexey Bochkovskiy and Chien-Yao Wang and Hong-Yuan Mark Liao}< / span > < span class = "p" > ,< / span >
< span class = "na" > year< / span > < span class = "p" > =< / span > < span class = "s" > {2020}< / span > < span class = "p" > ,< / span >
< span class = "na" > eprint< / span > < span class = "p" > =< / span > < span class = "s" > {2004.10934}< / 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" > primaryClass< / span > < span class = "p" > =< / span > < span class = "s" > {cs.CV}< / span >
< span class = "p" > }< / span >
< / code > < / pre > < / div >
<!--
Type: model-index
Collections:
- Name: CSP DarkNet
Paper:
Title: 'YOLOv4: Optimal Speed and Accuracy of Object Detection'
URL: https://paperswithcode.com/paper/yolov4-optimal-speed-and-accuracy-of-object
Models:
- Name: cspdarknet53
In Collection: CSP DarkNet
Metadata:
FLOPs: 8545018880
Parameters: 27640000
File Size: 110775135
Architecture:
- 1x1 Convolution
- Batch Normalization
- Convolution
- Global Average Pooling
- Mish
- Residual Connection
- Softmax
Tasks:
- Image Classification
Training Techniques:
- CutMix
- Label Smoothing
- Mosaic
- Polynomial Learning Rate Decay
- SGD with Momentum
- Self-Adversarial Training
- Weight Decay
Training Data:
- ImageNet
Training Resources: 1x NVIDIA RTX 2070 GPU
ID: cspdarknet53
LR: 0.1
Layers: 53
Crop Pct: '0.887'
Momentum: 0.9
Batch Size: 128
Image Size: '256'
Warmup Steps: 1000
Weight Decay: 0.0005
Interpolation: bilinear
Training Steps: 8000000
FPS (GPU RTX 2070): 66
Code: https://github.com/rwightman/pytorch-image-models/blob/d8e69206be253892b2956341fea09fdebfaae4e3/timm/models/cspnet.py#L441
Weights: https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/cspdarknet53_ra_256-d05c7c21.pth
Results:
- Task: Image Classification
Dataset: ImageNet
Metrics:
Top 1 Accuracy: 80.05%
Top 5 Accuracy: 95.09%
-->
< / article >
< / div >
< / div >
< / main >
< footer class = "md-footer" >
< nav class = "md-footer__inner md-grid" aria-label = "Footer" >
< a href = "../big-transfer/" 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 >
Big Transfer (BiT)
< / div >
< / div >
< / a >
< a href = "../csp-resnet/" 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 >
CSP-ResNet
< / 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 >
