2019-03-24 17:22:43 +00:00
<!DOCTYPE html>
<!-- [if IE 8]><html class="no - js lt - ie9" lang="en" > <![endif] -->
<!-- [if gt IE 8]><! --> < html class = "no-js" lang = "en" > <!-- <![endif] -->
< head >
< meta charset = "utf-8" >
< meta name = "viewport" content = "width=device-width, initial-scale=1.0" >
2019-04-27 23:32:21 +01:00
< title > torchreid.models.hacnn — torchreid 0.7.4 documentation< / title >
2019-03-24 17:22:43 +00:00
< script type = "text/javascript" src = "../../../_static/js/modernizr.min.js" > < / script >
< script type = "text/javascript" id = "documentation_options" data-url_root = "../../../" src = "../../../_static/documentation_options.js" > < / script >
< script type = "text/javascript" src = "../../../_static/jquery.js" > < / script >
< script type = "text/javascript" src = "../../../_static/underscore.js" > < / script >
< script type = "text/javascript" src = "../../../_static/doctools.js" > < / script >
< script type = "text/javascript" src = "../../../_static/language_data.js" > < / script >
< script async = "async" type = "text/javascript" src = "https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML" > < / script >
< script type = "text/javascript" src = "../../../_static/js/theme.js" > < / script >
< link rel = "stylesheet" href = "../../../_static/css/theme.css" type = "text/css" / >
< link rel = "stylesheet" href = "../../../_static/pygments.css" type = "text/css" / >
< link rel = "index" title = "Index" href = "../../../genindex.html" / >
< link rel = "search" title = "Search" href = "../../../search.html" / >
< / head >
< body class = "wy-body-for-nav" >
< div class = "wy-grid-for-nav" >
< nav data-toggle = "wy-nav-shift" class = "wy-nav-side" >
< div class = "wy-side-scroll" >
< div class = "wy-side-nav-search" >
< a href = "../../../index.html" class = "icon icon-home" > torchreid
< / a >
< div class = "version" >
2019-04-27 23:32:21 +01:00
0.7.4
2019-03-24 17:22:43 +00:00
< / div >
< div role = "search" >
< form id = "rtd-search-form" class = "wy-form" action = "../../../search.html" method = "get" >
< input type = "text" name = "q" placeholder = "Search docs" / >
< input type = "hidden" name = "check_keywords" value = "yes" / >
< input type = "hidden" name = "area" value = "default" / >
< / form >
< / div >
< / div >
< div class = "wy-menu wy-menu-vertical" data-spy = "affix" role = "navigation" aria-label = "main navigation" >
< ul >
< li class = "toctree-l1" > < a class = "reference internal" href = "../../../user_guide.html" > How-to< / a > < / li >
< li class = "toctree-l1" > < a class = "reference internal" href = "../../../datasets.html" > Datasets< / a > < / li >
< li class = "toctree-l1" > < a class = "reference internal" href = "../../../evaluation.html" > Evaluation< / a > < / li >
< / ul >
< p class = "caption" > < span class = "caption-text" > Package Reference< / span > < / p >
< ul >
< li class = "toctree-l1" > < a class = "reference internal" href = "../../../pkg/data.html" > torchreid.data< / a > < / li >
< li class = "toctree-l1" > < a class = "reference internal" href = "../../../pkg/engine.html" > torchreid.engine< / a > < / li >
< li class = "toctree-l1" > < a class = "reference internal" href = "../../../pkg/losses.html" > torchreid.losses< / a > < / li >
< li class = "toctree-l1" > < a class = "reference internal" href = "../../../pkg/metrics.html" > torchreid.metrics< / a > < / li >
< li class = "toctree-l1" > < a class = "reference internal" href = "../../../pkg/models.html" > torchreid.models< / a > < / li >
< li class = "toctree-l1" > < a class = "reference internal" href = "../../../pkg/optim.html" > torchreid.optim< / a > < / li >
< li class = "toctree-l1" > < a class = "reference internal" href = "../../../pkg/utils.html" > torchreid.utils< / a > < / li >
< / ul >
< p class = "caption" > < span class = "caption-text" > Resources< / span > < / p >
< ul >
< li class = "toctree-l1" > < a class = "reference internal" href = "../../../AWESOME_REID.html" > Awesome-ReID< / a > < / li >
< li class = "toctree-l1" > < a class = "reference internal" href = "../../../MODEL_ZOO.html" > Model Zoo< / a > < / li >
< / ul >
< / div >
< / div >
< / nav >
< section data-toggle = "wy-nav-shift" class = "wy-nav-content-wrap" >
< nav class = "wy-nav-top" aria-label = "top navigation" >
< i data-toggle = "wy-nav-top" class = "fa fa-bars" > < / i >
< a href = "../../../index.html" > torchreid< / a >
< / nav >
< div class = "wy-nav-content" >
< div class = "rst-content" >
< div role = "navigation" aria-label = "breadcrumbs navigation" >
< ul class = "wy-breadcrumbs" >
< li > < a href = "../../../index.html" > Docs< / a > » < / li >
< li > < a href = "../../index.html" > Module code< / a > » < / li >
< li > torchreid.models.hacnn< / li >
< li class = "wy-breadcrumbs-aside" >
< / li >
< / ul >
< hr / >
< / div >
< div role = "main" class = "document" itemscope = "itemscope" itemtype = "http://schema.org/Article" >
< div itemprop = "articleBody" >
< h1 > Source code for torchreid.models.hacnn< / h1 > < div class = "highlight" > < pre >
< span > < / span > < span class = "kn" > from< / span > < span class = "nn" > __future__< / span > < span class = "k" > import< / span > < span class = "n" > absolute_import< / span >
< span class = "kn" > from< / span > < span class = "nn" > __future__< / span > < span class = "k" > import< / span > < span class = "n" > division< / span >
< span class = "n" > __all__< / span > < span class = "o" > =< / span > < span class = "p" > [< / span > < span class = "s1" > ' HACNN' < / span > < span class = "p" > ]< / span >
< span class = "kn" > import< / span > < span class = "nn" > torch< / span >
< span class = "kn" > from< / span > < span class = "nn" > torch< / span > < span class = "k" > import< / span > < span class = "n" > nn< / span >
< span class = "kn" > from< / span > < span class = "nn" > torch.nn< / span > < span class = "k" > import< / span > < span class = "n" > functional< / span > < span class = "k" > as< / span > < span class = "n" > F< / span >
< span class = "kn" > import< / span > < span class = "nn" > torchvision< / span >
< span class = "k" > class< / span > < span class = "nc" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Module< / span > < span class = "p" > ):< / span >
< span class = "sd" > " " " Basic convolutional block.< / span >
< span class = "sd" > < / span >
< span class = "sd" > convolution + batch normalization + relu.< / span >
< span class = "sd" > Args:< / span >
< span class = "sd" > in_c (int): number of input channels.< / span >
< span class = "sd" > out_c (int): number of output channels.< / span >
< span class = "sd" > k (int or tuple): kernel size.< / span >
< span class = "sd" > s (int or tuple): stride.< / span >
< span class = "sd" > p (int or tuple): padding.< / span >
< span class = "sd" > " " " < / span >
< span class = "k" > def< / span > < span class = "nf" > __init__< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > in_c< / span > < span class = "p" > ,< / span > < span class = "n" > out_c< / span > < span class = "p" > ,< / span > < span class = "n" > k< / span > < span class = "p" > ,< / span > < span class = "n" > s< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > ,< / span > < span class = "n" > p< / span > < span class = "o" > =< / span > < span class = "mi" > 0< / span > < span class = "p" > ):< / span >
< span class = "nb" > super< / span > < span class = "p" > (< / span > < span class = "n" > ConvBlock< / span > < span class = "p" > ,< / span > < span class = "bp" > self< / span > < span class = "p" > )< / span > < span class = "o" > .< / span > < span class = "fm" > __init__< / span > < span class = "p" > ()< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > conv< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Conv2d< / span > < span class = "p" > (< / span > < span class = "n" > in_c< / span > < span class = "p" > ,< / span > < span class = "n" > out_c< / span > < span class = "p" > ,< / span > < span class = "n" > k< / span > < span class = "p" > ,< / span > < span class = "n" > stride< / span > < span class = "o" > =< / span > < span class = "n" > s< / span > < span class = "p" > ,< / span > < span class = "n" > padding< / span > < span class = "o" > =< / span > < span class = "n" > p< / span > < span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > bn< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > BatchNorm2d< / span > < span class = "p" > (< / span > < span class = "n" > out_c< / span > < span class = "p" > )< / span >
< span class = "k" > def< / span > < span class = "nf" > forward< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > x< / span > < span class = "p" > ):< / span >
< span class = "k" > return< / span > < span class = "n" > F< / span > < span class = "o" > .< / span > < span class = "n" > relu< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > bn< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > conv< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )))< / span >
< span class = "k" > class< / span > < span class = "nc" > InceptionA< / span > < span class = "p" > (< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Module< / span > < span class = "p" > ):< / span >
< span class = "k" > def< / span > < span class = "nf" > __init__< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "n" > out_channels< / span > < span class = "p" > ):< / span >
< span class = "nb" > super< / span > < span class = "p" > (< / span > < span class = "n" > InceptionA< / span > < span class = "p" > ,< / span > < span class = "bp" > self< / span > < span class = "p" > )< / span > < span class = "o" > .< / span > < span class = "fm" > __init__< / span > < span class = "p" > ()< / span >
< span class = "n" > mid_channels< / span > < span class = "o" > =< / span > < span class = "n" > out_channels< / span > < span class = "o" > //< / span > < span class = "mi" > 4< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stream1< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Sequential< / span > < span class = "p" > (< / span >
< span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 3< / span > < span class = "p" > ,< / span > < span class = "n" > p< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stream2< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Sequential< / span > < span class = "p" > (< / span >
< span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 3< / span > < span class = "p" > ,< / span > < span class = "n" > p< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stream3< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Sequential< / span > < span class = "p" > (< / span >
< span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 3< / span > < span class = "p" > ,< / span > < span class = "n" > p< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stream4< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Sequential< / span > < span class = "p" > (< / span >
< span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > AvgPool2d< / span > < span class = "p" > (< / span > < span class = "mi" > 3< / span > < span class = "p" > ,< / span > < span class = "n" > stride< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > ,< / span > < span class = "n" > padding< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "p" > )< / span >
< span class = "k" > def< / span > < span class = "nf" > forward< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > x< / span > < span class = "p" > ):< / span >
< span class = "n" > s1< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stream1< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "n" > s2< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stream2< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "n" > s3< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stream3< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "n" > s4< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stream4< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "n" > y< / span > < span class = "o" > =< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > cat< / span > < span class = "p" > ([< / span > < span class = "n" > s1< / span > < span class = "p" > ,< / span > < span class = "n" > s2< / span > < span class = "p" > ,< / span > < span class = "n" > s3< / span > < span class = "p" > ,< / span > < span class = "n" > s4< / span > < span class = "p" > ],< / span > < span class = "n" > dim< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > )< / span >
< span class = "k" > return< / span > < span class = "n" > y< / span >
< span class = "k" > class< / span > < span class = "nc" > InceptionB< / span > < span class = "p" > (< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Module< / span > < span class = "p" > ):< / span >
< span class = "k" > def< / span > < span class = "nf" > __init__< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "n" > out_channels< / span > < span class = "p" > ):< / span >
< span class = "nb" > super< / span > < span class = "p" > (< / span > < span class = "n" > InceptionB< / span > < span class = "p" > ,< / span > < span class = "bp" > self< / span > < span class = "p" > )< / span > < span class = "o" > .< / span > < span class = "fm" > __init__< / span > < span class = "p" > ()< / span >
< span class = "n" > mid_channels< / span > < span class = "o" > =< / span > < span class = "n" > out_channels< / span > < span class = "o" > //< / span > < span class = "mi" > 4< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stream1< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Sequential< / span > < span class = "p" > (< / span >
< span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 3< / span > < span class = "p" > ,< / span > < span class = "n" > s< / span > < span class = "o" > =< / span > < span class = "mi" > 2< / span > < span class = "p" > ,< / span > < span class = "n" > p< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stream2< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Sequential< / span > < span class = "p" > (< / span >
< span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 3< / span > < span class = "p" > ,< / span > < span class = "n" > p< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "n" > mid_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 3< / span > < span class = "p" > ,< / span > < span class = "n" > s< / span > < span class = "o" > =< / span > < span class = "mi" > 2< / span > < span class = "p" > ,< / span > < span class = "n" > p< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stream3< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Sequential< / span > < span class = "p" > (< / span >
< span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > MaxPool2d< / span > < span class = "p" > (< / span > < span class = "mi" > 3< / span > < span class = "p" > ,< / span > < span class = "n" > stride< / span > < span class = "o" > =< / span > < span class = "mi" > 2< / span > < span class = "p" > ,< / span > < span class = "n" > padding< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "n" > mid_channels< / span > < span class = "o" > *< / span > < span class = "mi" > 2< / span > < span class = "p" > ,< / span > < span class = "mi" > 1< / span > < span class = "p" > ),< / span >
< span class = "p" > )< / span >
< span class = "k" > def< / span > < span class = "nf" > forward< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > x< / span > < span class = "p" > ):< / span >
< span class = "n" > s1< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stream1< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "n" > s2< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stream2< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "n" > s3< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stream3< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "n" > y< / span > < span class = "o" > =< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > cat< / span > < span class = "p" > ([< / span > < span class = "n" > s1< / span > < span class = "p" > ,< / span > < span class = "n" > s2< / span > < span class = "p" > ,< / span > < span class = "n" > s3< / span > < span class = "p" > ],< / span > < span class = "n" > dim< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > )< / span >
< span class = "k" > return< / span > < span class = "n" > y< / span >
< span class = "k" > class< / span > < span class = "nc" > SpatialAttn< / span > < span class = "p" > (< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Module< / span > < span class = "p" > ):< / span >
< span class = "sd" > " " " Spatial Attention (Sec. 3.1.I.1)" " " < / span >
< span class = "k" > def< / span > < span class = "nf" > __init__< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ):< / span >
< span class = "nb" > super< / span > < span class = "p" > (< / span > < span class = "n" > SpatialAttn< / span > < span class = "p" > ,< / span > < span class = "bp" > self< / span > < span class = "p" > )< / span > < span class = "o" > .< / span > < span class = "fm" > __init__< / span > < span class = "p" > ()< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > conv1< / span > < span class = "o" > =< / span > < span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "mi" > 1< / span > < span class = "p" > ,< / span > < span class = "mi" > 1< / span > < span class = "p" > ,< / span > < span class = "mi" > 3< / span > < span class = "p" > ,< / span > < span class = "n" > s< / span > < span class = "o" > =< / span > < span class = "mi" > 2< / span > < span class = "p" > ,< / span > < span class = "n" > p< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > conv2< / span > < span class = "o" > =< / span > < span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "mi" > 1< / span > < span class = "p" > ,< / span > < span class = "mi" > 1< / span > < span class = "p" > ,< / span > < span class = "mi" > 1< / span > < span class = "p" > )< / span >
< span class = "k" > def< / span > < span class = "nf" > forward< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > x< / span > < span class = "p" > ):< / span >
< span class = "c1" > # global cross-channel averaging< / span >
< span class = "n" > x< / span > < span class = "o" > =< / span > < span class = "n" > x< / span > < span class = "o" > .< / span > < span class = "n" > mean< / span > < span class = "p" > (< / span > < span class = "mi" > 1< / span > < span class = "p" > ,< / span > < span class = "n" > keepdim< / span > < span class = "o" > =< / span > < span class = "kc" > True< / span > < span class = "p" > )< / span >
< span class = "c1" > # 3-by-3 conv< / span >
< span class = "n" > x< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > conv1< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "c1" > # bilinear resizing< / span >
< span class = "n" > x< / span > < span class = "o" > =< / span > < span class = "n" > F< / span > < span class = "o" > .< / span > < span class = "n" > upsample< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > ,< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "o" > .< / span > < span class = "n" > size< / span > < span class = "p" > (< / span > < span class = "mi" > 2< / span > < span class = "p" > )< / span > < span class = "o" > *< / span > < span class = "mi" > 2< / span > < span class = "p" > ,< / span > < span class = "n" > x< / span > < span class = "o" > .< / span > < span class = "n" > size< / span > < span class = "p" > (< / span > < span class = "mi" > 3< / span > < span class = "p" > )< / span > < span class = "o" > *< / span > < span class = "mi" > 2< / span > < span class = "p" > ),< / span > < span class = "n" > mode< / span > < span class = "o" > =< / span > < span class = "s1" > ' bilinear' < / span > < span class = "p" > ,< / span > < span class = "n" > align_corners< / span > < span class = "o" > =< / span > < span class = "kc" > True< / span > < span class = "p" > )< / span >
< span class = "c1" > # scaling conv< / span >
< span class = "n" > x< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > conv2< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "k" > return< / span > < span class = "n" > x< / span >
< span class = "k" > class< / span > < span class = "nc" > ChannelAttn< / span > < span class = "p" > (< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Module< / span > < span class = "p" > ):< / span >
< span class = "sd" > " " " Channel Attention (Sec. 3.1.I.2)" " " < / span >
< span class = "k" > def< / span > < span class = "nf" > __init__< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "n" > reduction_rate< / span > < span class = "o" > =< / span > < span class = "mi" > 16< / span > < span class = "p" > ):< / span >
< span class = "nb" > super< / span > < span class = "p" > (< / span > < span class = "n" > ChannelAttn< / span > < span class = "p" > ,< / span > < span class = "bp" > self< / span > < span class = "p" > )< / span > < span class = "o" > .< / span > < span class = "fm" > __init__< / span > < span class = "p" > ()< / span >
< span class = "k" > assert< / span > < span class = "n" > in_channels< / span > < span class = "o" > %< / span > < span class = "n" > reduction_rate< / span > < span class = "o" > ==< / span > < span class = "mi" > 0< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > conv1< / span > < span class = "o" > =< / span > < span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "n" > in_channels< / span > < span class = "o" > //< / span > < span class = "n" > reduction_rate< / span > < span class = "p" > ,< / span > < span class = "mi" > 1< / span > < span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > conv2< / span > < span class = "o" > =< / span > < span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > in_channels< / span > < span class = "o" > //< / span > < span class = "n" > reduction_rate< / span > < span class = "p" > ,< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 1< / span > < span class = "p" > )< / span >
< span class = "k" > def< / span > < span class = "nf" > forward< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > x< / span > < span class = "p" > ):< / span >
< span class = "c1" > # squeeze operation (global average pooling)< / span >
< span class = "n" > x< / span > < span class = "o" > =< / span > < span class = "n" > F< / span > < span class = "o" > .< / span > < span class = "n" > avg_pool2d< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > ,< / span > < span class = "n" > x< / span > < span class = "o" > .< / span > < span class = "n" > size< / span > < span class = "p" > ()[< / span > < span class = "mi" > 2< / span > < span class = "p" > :])< / span >
< span class = "c1" > # excitation operation (2 conv layers)< / span >
< span class = "n" > x< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > conv1< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "n" > x< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > conv2< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "k" > return< / span > < span class = "n" > x< / span >
< span class = "k" > class< / span > < span class = "nc" > SoftAttn< / span > < span class = "p" > (< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Module< / span > < span class = "p" > ):< / span >
< span class = "sd" > " " " Soft Attention (Sec. 3.1.I)< / span >
< span class = "sd" > < / span >
< span class = "sd" > Aim: Spatial Attention + Channel Attention< / span >
< span class = "sd" > < / span >
< span class = "sd" > Output: attention maps with shape identical to input.< / span >
< span class = "sd" > " " " < / span >
< span class = "k" > def< / span > < span class = "nf" > __init__< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > in_channels< / span > < span class = "p" > ):< / span >
< span class = "nb" > super< / span > < span class = "p" > (< / span > < span class = "n" > SoftAttn< / span > < span class = "p" > ,< / span > < span class = "bp" > self< / span > < span class = "p" > )< / span > < span class = "o" > .< / span > < span class = "fm" > __init__< / span > < span class = "p" > ()< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > spatial_attn< / span > < span class = "o" > =< / span > < span class = "n" > SpatialAttn< / span > < span class = "p" > ()< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > channel_attn< / span > < span class = "o" > =< / span > < span class = "n" > ChannelAttn< / span > < span class = "p" > (< / span > < span class = "n" > in_channels< / span > < span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > conv< / span > < span class = "o" > =< / span > < span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 1< / span > < span class = "p" > )< / span >
< span class = "k" > def< / span > < span class = "nf" > forward< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > x< / span > < span class = "p" > ):< / span >
< span class = "n" > y_spatial< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > spatial_attn< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "n" > y_channel< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > channel_attn< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "n" > y< / span > < span class = "o" > =< / span > < span class = "n" > y_spatial< / span > < span class = "o" > *< / span > < span class = "n" > y_channel< / span >
< span class = "n" > y< / span > < span class = "o" > =< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > sigmoid< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > conv< / span > < span class = "p" > (< / span > < span class = "n" > y< / span > < span class = "p" > ))< / span >
< span class = "k" > return< / span > < span class = "n" > y< / span >
< span class = "k" > class< / span > < span class = "nc" > HardAttn< / span > < span class = "p" > (< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Module< / span > < span class = "p" > ):< / span >
< span class = "sd" > " " " Hard Attention (Sec. 3.1.II)" " " < / span >
< span class = "k" > def< / span > < span class = "nf" > __init__< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > in_channels< / span > < span class = "p" > ):< / span >
< span class = "nb" > super< / span > < span class = "p" > (< / span > < span class = "n" > HardAttn< / span > < span class = "p" > ,< / span > < span class = "bp" > self< / span > < span class = "p" > )< / span > < span class = "o" > .< / span > < span class = "fm" > __init__< / span > < span class = "p" > ()< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > fc< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Linear< / span > < span class = "p" > (< / span > < span class = "n" > in_channels< / span > < span class = "p" > ,< / span > < span class = "mi" > 4< / span > < span class = "o" > *< / span > < span class = "mi" > 2< / span > < span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > init_params< / span > < span class = "p" > ()< / span >
< span class = "k" > def< / span > < span class = "nf" > init_params< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ):< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > fc< / span > < span class = "o" > .< / span > < span class = "n" > weight< / span > < span class = "o" > .< / span > < span class = "n" > data< / span > < span class = "o" > .< / span > < span class = "n" > zero_< / span > < span class = "p" > ()< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > fc< / span > < span class = "o" > .< / span > < span class = "n" > bias< / span > < span class = "o" > .< / span > < span class = "n" > data< / span > < span class = "o" > .< / span > < span class = "n" > copy_< / span > < span class = "p" > (< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > tensor< / span > < span class = "p" > ([< / span > < span class = "mi" > 0< / span > < span class = "p" > ,< / span > < span class = "o" > -< / span > < span class = "mf" > 0.75< / span > < span class = "p" > ,< / span > < span class = "mi" > 0< / span > < span class = "p" > ,< / span > < span class = "o" > -< / span > < span class = "mf" > 0.25< / span > < span class = "p" > ,< / span > < span class = "mi" > 0< / span > < span class = "p" > ,< / span > < span class = "mf" > 0.25< / span > < span class = "p" > ,< / span > < span class = "mi" > 0< / span > < span class = "p" > ,< / span > < span class = "mf" > 0.75< / span > < span class = "p" > ],< / span > < span class = "n" > dtype< / span > < span class = "o" > =< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > float< / span > < span class = "p" > ))< / span >
< span class = "k" > def< / span > < span class = "nf" > forward< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > x< / span > < span class = "p" > ):< / span >
< span class = "c1" > # squeeze operation (global average pooling)< / span >
< span class = "n" > x< / span > < span class = "o" > =< / span > < span class = "n" > F< / span > < span class = "o" > .< / span > < span class = "n" > avg_pool2d< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > ,< / span > < span class = "n" > x< / span > < span class = "o" > .< / span > < span class = "n" > size< / span > < span class = "p" > ()[< / span > < span class = "mi" > 2< / span > < span class = "p" > :])< / span > < span class = "o" > .< / span > < span class = "n" > view< / span > < span class = "p" > (< / span > < span class = "n" > x< / 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 = "n" > x< / span > < span class = "o" > .< / span > < span class = "n" > size< / span > < span class = "p" > (< / span > < span class = "mi" > 1< / span > < span class = "p" > ))< / span >
< span class = "c1" > # predict transformation parameters< / span >
< span class = "n" > theta< / span > < span class = "o" > =< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > tanh< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > fc< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > ))< / span >
< span class = "n" > theta< / span > < span class = "o" > =< / span > < span class = "n" > theta< / span > < span class = "o" > .< / span > < span class = "n" > view< / span > < span class = "p" > (< / span > < span class = "o" > -< / span > < span class = "mi" > 1< / span > < span class = "p" > ,< / span > < span class = "mi" > 4< / span > < span class = "p" > ,< / span > < span class = "mi" > 2< / span > < span class = "p" > )< / span >
< span class = "k" > return< / span > < span class = "n" > theta< / span >
< span class = "k" > class< / span > < span class = "nc" > HarmAttn< / span > < span class = "p" > (< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Module< / span > < span class = "p" > ):< / span >
< span class = "sd" > " " " Harmonious Attention (Sec. 3.1)" " " < / span >
< span class = "k" > def< / span > < span class = "nf" > __init__< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > in_channels< / span > < span class = "p" > ):< / span >
< span class = "nb" > super< / span > < span class = "p" > (< / span > < span class = "n" > HarmAttn< / span > < span class = "p" > ,< / span > < span class = "bp" > self< / span > < span class = "p" > )< / span > < span class = "o" > .< / span > < span class = "fm" > __init__< / span > < span class = "p" > ()< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > soft_attn< / span > < span class = "o" > =< / span > < span class = "n" > SoftAttn< / span > < span class = "p" > (< / span > < span class = "n" > in_channels< / span > < span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > hard_attn< / span > < span class = "o" > =< / span > < span class = "n" > HardAttn< / span > < span class = "p" > (< / span > < span class = "n" > in_channels< / span > < span class = "p" > )< / span >
< span class = "k" > def< / span > < span class = "nf" > forward< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > x< / span > < span class = "p" > ):< / span >
< span class = "n" > y_soft_attn< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > soft_attn< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "n" > theta< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > hard_attn< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "k" > return< / span > < span class = "n" > y_soft_attn< / span > < span class = "p" > ,< / span > < span class = "n" > theta< / span >
< div class = "viewcode-block" id = "HACNN" > < a class = "viewcode-back" href = "../../../pkg/models.html#torchreid.models.hacnn.HACNN" > [docs]< / a > < span class = "k" > class< / span > < span class = "nc" > HACNN< / span > < span class = "p" > (< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Module< / span > < span class = "p" > ):< / span >
< span class = "sd" > " " " Harmonious Attention Convolutional Neural Network.< / span >
< span class = "sd" > Reference:< / span >
< span class = "sd" > Li et al. Harmonious Attention Network for Person Re-identification. CVPR 2018.< / span >
< span class = "sd" > Public keys:< / span >
< span class = "sd" > - ``hacnn``: HACNN.< / span >
< span class = "sd" > " " " < / span >
< span class = "c1" > # Args:< / span >
< span class = "c1" > # num_classes (int): number of classes to predict< / span >
< span class = "c1" > # nchannels (list): number of channels AFTER concatenation< / span >
< span class = "c1" > # feat_dim (int): feature dimension for a single stream< / span >
< span class = "c1" > # learn_region (bool): whether to learn region features (i.e. local branch)< / span >
< span class = "k" > def< / span > < span class = "nf" > __init__< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > num_classes< / span > < span class = "p" > ,< / span > < span class = "n" > loss< / span > < span class = "o" > =< / span > < span class = "s1" > ' softmax' < / span > < span class = "p" > ,< / span > < span class = "n" > nchannels< / span > < span class = "o" > =< / span > < span class = "p" > [< / span > < span class = "mi" > 128< / span > < span class = "p" > ,< / span > < span class = "mi" > 256< / span > < span class = "p" > ,< / span > < span class = "mi" > 384< / span > < span class = "p" > ],< / span > < span class = "n" > feat_dim< / span > < span class = "o" > =< / span > < span class = "mi" > 512< / span > < span class = "p" > ,< / span > < span class = "n" > learn_region< / span > < span class = "o" > =< / span > < span class = "kc" > True< / span > < span class = "p" > ,< / span > < span class = "n" > use_gpu< / span > < span class = "o" > =< / span > < span class = "kc" > True< / span > < span class = "p" > ,< / span > < span class = "o" > **< / span > < span class = "n" > kwargs< / span > < span class = "p" > ):< / span >
< span class = "nb" > super< / span > < span class = "p" > (< / span > < span class = "n" > HACNN< / span > < span class = "p" > ,< / span > < span class = "bp" > self< / span > < span class = "p" > )< / span > < span class = "o" > .< / span > < span class = "fm" > __init__< / span > < span class = "p" > ()< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > loss< / span > < span class = "o" > =< / span > < span class = "n" > loss< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > learn_region< / span > < span class = "o" > =< / span > < span class = "n" > learn_region< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > use_gpu< / span > < span class = "o" > =< / span > < span class = "n" > use_gpu< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > conv< / span > < span class = "o" > =< / span > < span class = "n" > ConvBlock< / span > < span class = "p" > (< / span > < span class = "mi" > 3< / span > < span class = "p" > ,< / span > < span class = "mi" > 32< / span > < span class = "p" > ,< / span > < span class = "mi" > 3< / span > < span class = "p" > ,< / span > < span class = "n" > s< / span > < span class = "o" > =< / span > < span class = "mi" > 2< / span > < span class = "p" > ,< / span > < span class = "n" > p< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > )< / span >
< span class = "c1" > # Construct Inception + HarmAttn blocks< / span >
< span class = "c1" > # ============== Block 1 ==============< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > inception1< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Sequential< / span > < span class = "p" > (< / span >
< span class = "n" > InceptionA< / span > < span class = "p" > (< / span > < span class = "mi" > 32< / span > < span class = "p" > ,< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 0< / span > < span class = "p" > ]),< / span >
< span class = "n" > InceptionB< / span > < span class = "p" > (< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 0< / span > < span class = "p" > ],< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 0< / span > < span class = "p" > ]),< / span >
< span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > ha1< / span > < span class = "o" > =< / span > < span class = "n" > HarmAttn< / span > < span class = "p" > (< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 0< / span > < span class = "p" > ])< / span >
< span class = "c1" > # ============== Block 2 ==============< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > inception2< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Sequential< / span > < span class = "p" > (< / span >
< span class = "n" > InceptionA< / span > < span class = "p" > (< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 0< / span > < span class = "p" > ],< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 1< / span > < span class = "p" > ]),< / span >
< span class = "n" > InceptionB< / span > < span class = "p" > (< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 1< / span > < span class = "p" > ],< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 1< / span > < span class = "p" > ]),< / span >
< span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > ha2< / span > < span class = "o" > =< / span > < span class = "n" > HarmAttn< / span > < span class = "p" > (< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 1< / span > < span class = "p" > ])< / span >
< span class = "c1" > # ============== Block 3 ==============< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > inception3< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Sequential< / span > < span class = "p" > (< / span >
< span class = "n" > InceptionA< / span > < span class = "p" > (< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 1< / span > < span class = "p" > ],< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 2< / span > < span class = "p" > ]),< / span >
< span class = "n" > InceptionB< / span > < span class = "p" > (< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 2< / span > < span class = "p" > ],< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 2< / span > < span class = "p" > ]),< / span >
< span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > ha3< / span > < span class = "o" > =< / span > < span class = "n" > HarmAttn< / span > < span class = "p" > (< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 2< / span > < span class = "p" > ])< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > fc_global< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Sequential< / span > < span class = "p" > (< / span >
< span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Linear< / span > < span class = "p" > (< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 2< / span > < span class = "p" > ],< / span > < span class = "n" > feat_dim< / span > < span class = "p" > ),< / span >
< span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > BatchNorm1d< / span > < span class = "p" > (< / span > < span class = "n" > feat_dim< / span > < span class = "p" > ),< / span >
< span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > ReLU< / span > < span class = "p" > (),< / span >
< span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > classifier_global< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Linear< / span > < span class = "p" > (< / span > < span class = "n" > feat_dim< / span > < span class = "p" > ,< / span > < span class = "n" > num_classes< / span > < span class = "p" > )< / span >
< span class = "k" > if< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > learn_region< / span > < span class = "p" > :< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > init_scale_factors< / span > < span class = "p" > ()< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > local_conv1< / span > < span class = "o" > =< / span > < span class = "n" > InceptionB< / span > < span class = "p" > (< / span > < span class = "mi" > 32< / span > < span class = "p" > ,< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 0< / span > < span class = "p" > ])< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > local_conv2< / span > < span class = "o" > =< / span > < span class = "n" > InceptionB< / span > < span class = "p" > (< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 0< / span > < span class = "p" > ],< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 1< / span > < span class = "p" > ])< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > local_conv3< / span > < span class = "o" > =< / span > < span class = "n" > InceptionB< / span > < span class = "p" > (< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 1< / span > < span class = "p" > ],< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 2< / span > < span class = "p" > ])< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > fc_local< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Sequential< / span > < span class = "p" > (< / span >
< span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Linear< / span > < span class = "p" > (< / span > < span class = "n" > nchannels< / span > < span class = "p" > [< / span > < span class = "mi" > 2< / span > < span class = "p" > ]< / span > < span class = "o" > *< / span > < span class = "mi" > 4< / span > < span class = "p" > ,< / span > < span class = "n" > feat_dim< / span > < span class = "p" > ),< / span >
< span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > BatchNorm1d< / span > < span class = "p" > (< / span > < span class = "n" > feat_dim< / span > < span class = "p" > ),< / span >
< span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > ReLU< / span > < span class = "p" > (),< / span >
< span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > classifier_local< / span > < span class = "o" > =< / span > < span class = "n" > nn< / span > < span class = "o" > .< / span > < span class = "n" > Linear< / span > < span class = "p" > (< / span > < span class = "n" > feat_dim< / span > < span class = "p" > ,< / span > < span class = "n" > num_classes< / span > < span class = "p" > )< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > feat_dim< / span > < span class = "o" > =< / span > < span class = "n" > feat_dim< / span > < span class = "o" > *< / span > < span class = "mi" > 2< / span >
< span class = "k" > else< / span > < span class = "p" > :< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > feat_dim< / span > < span class = "o" > =< / span > < span class = "n" > feat_dim< / span >
< span class = "k" > def< / span > < span class = "nf" > init_scale_factors< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ):< / span >
< span class = "c1" > # initialize scale factors (s_w, s_h) for four regions< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > scale_factors< / span > < span class = "o" > =< / span > < span class = "p" > []< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > scale_factors< / span > < span class = "o" > .< / span > < span class = "n" > append< / span > < span class = "p" > (< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > tensor< / span > < span class = "p" > ([[< / span > < span class = "mi" > 1< / span > < span class = "p" > ,< / span > < span class = "mi" > 0< / span > < span class = "p" > ],< / span > < span class = "p" > [< / span > < span class = "mi" > 0< / span > < span class = "p" > ,< / span > < span class = "mf" > 0.25< / span > < span class = "p" > ]],< / span > < span class = "n" > dtype< / span > < span class = "o" > =< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > float< / span > < span class = "p" > ))< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > scale_factors< / span > < span class = "o" > .< / span > < span class = "n" > append< / span > < span class = "p" > (< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > tensor< / span > < span class = "p" > ([[< / span > < span class = "mi" > 1< / span > < span class = "p" > ,< / span > < span class = "mi" > 0< / span > < span class = "p" > ],< / span > < span class = "p" > [< / span > < span class = "mi" > 0< / span > < span class = "p" > ,< / span > < span class = "mf" > 0.25< / span > < span class = "p" > ]],< / span > < span class = "n" > dtype< / span > < span class = "o" > =< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > float< / span > < span class = "p" > ))< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > scale_factors< / span > < span class = "o" > .< / span > < span class = "n" > append< / span > < span class = "p" > (< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > tensor< / span > < span class = "p" > ([[< / span > < span class = "mi" > 1< / span > < span class = "p" > ,< / span > < span class = "mi" > 0< / span > < span class = "p" > ],< / span > < span class = "p" > [< / span > < span class = "mi" > 0< / span > < span class = "p" > ,< / span > < span class = "mf" > 0.25< / span > < span class = "p" > ]],< / span > < span class = "n" > dtype< / span > < span class = "o" > =< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > float< / span > < span class = "p" > ))< / span >
< span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > scale_factors< / span > < span class = "o" > .< / span > < span class = "n" > append< / span > < span class = "p" > (< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > tensor< / span > < span class = "p" > ([[< / span > < span class = "mi" > 1< / span > < span class = "p" > ,< / span > < span class = "mi" > 0< / span > < span class = "p" > ],< / span > < span class = "p" > [< / span > < span class = "mi" > 0< / span > < span class = "p" > ,< / span > < span class = "mf" > 0.25< / span > < span class = "p" > ]],< / span > < span class = "n" > dtype< / span > < span class = "o" > =< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > float< / span > < span class = "p" > ))< / span >
< span class = "k" > def< / span > < span class = "nf" > stn< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > x< / span > < span class = "p" > ,< / span > < span class = "n" > theta< / span > < span class = "p" > ):< / span >
< span class = "sd" > " " " Performs spatial transform< / span >
< span class = "sd" > < / span >
< span class = "sd" > x: (batch, channel, height, width)< / span >
< span class = "sd" > theta: (batch, 2, 3)< / span >
< span class = "sd" > " " " < / span >
< span class = "n" > grid< / span > < span class = "o" > =< / span > < span class = "n" > F< / span > < span class = "o" > .< / span > < span class = "n" > affine_grid< / span > < span class = "p" > (< / span > < span class = "n" > theta< / span > < span class = "p" > ,< / span > < span class = "n" > x< / span > < span class = "o" > .< / span > < span class = "n" > size< / span > < span class = "p" > ())< / span >
< span class = "n" > x< / span > < span class = "o" > =< / span > < span class = "n" > F< / span > < span class = "o" > .< / span > < span class = "n" > grid_sample< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > ,< / span > < span class = "n" > grid< / span > < span class = "p" > )< / span >
< span class = "k" > return< / span > < span class = "n" > x< / span >
< span class = "k" > def< / span > < span class = "nf" > transform_theta< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > theta_i< / span > < span class = "p" > ,< / span > < span class = "n" > region_idx< / span > < span class = "p" > ):< / span >
< span class = "sd" > " " " Transforms theta to include (s_w, s_h), resulting in (batch, 2, 3)" " " < / span >
< span class = "n" > scale_factors< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > scale_factors< / span > < span class = "p" > [< / span > < span class = "n" > region_idx< / span > < span class = "p" > ]< / span >
< span class = "n" > theta< / span > < span class = "o" > =< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > zeros< / span > < span class = "p" > (< / span > < span class = "n" > theta_i< / 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 = "mi" > 2< / span > < span class = "p" > ,< / span > < span class = "mi" > 3< / span > < span class = "p" > )< / span >
< span class = "n" > theta< / span > < span class = "p" > [:,:,:< / span > < span class = "mi" > 2< / span > < span class = "p" > ]< / span > < span class = "o" > =< / span > < span class = "n" > scale_factors< / span >
< span class = "n" > theta< / span > < span class = "p" > [:,:,< / span > < span class = "o" > -< / span > < span class = "mi" > 1< / span > < span class = "p" > ]< / span > < span class = "o" > =< / span > < span class = "n" > theta_i< / span >
< span class = "k" > if< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > use_gpu< / span > < span class = "p" > :< / span > < span class = "n" > theta< / span > < span class = "o" > =< / span > < span class = "n" > theta< / span > < span class = "o" > .< / span > < span class = "n" > cuda< / span > < span class = "p" > ()< / span >
< span class = "k" > return< / span > < span class = "n" > theta< / span >
< span class = "k" > def< / span > < span class = "nf" > forward< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "p" > ,< / span > < span class = "n" > x< / span > < span class = "p" > ):< / span >
< span class = "k" > assert< / span > < span class = "n" > x< / span > < span class = "o" > .< / span > < span class = "n" > size< / span > < span class = "p" > (< / span > < span class = "mi" > 2< / span > < span class = "p" > )< / span > < span class = "o" > ==< / span > < span class = "mi" > 160< / span > < span class = "ow" > and< / span > < span class = "n" > x< / span > < span class = "o" > .< / span > < span class = "n" > size< / span > < span class = "p" > (< / span > < span class = "mi" > 3< / span > < span class = "p" > )< / span > < span class = "o" > ==< / span > < span class = "mi" > 64< / span > < span class = "p" > ,< / span > \
< span class = "s1" > ' Input size does not match, expected (160, 64) but got (< / span > < span class = "si" > {}< / span > < span class = "s1" > , < / span > < span class = "si" > {}< / span > < span class = "s1" > )' < / span > < span class = "o" > .< / span > < span class = "n" > format< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "o" > .< / span > < span class = "n" > size< / span > < span class = "p" > (< / span > < span class = "mi" > 2< / span > < span class = "p" > ),< / span > < span class = "n" > x< / span > < span class = "o" > .< / span > < span class = "n" > size< / span > < span class = "p" > (< / span > < span class = "mi" > 3< / span > < span class = "p" > ))< / span >
< span class = "n" > x< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > conv< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "c1" > # ============== Block 1 ==============< / span >
< span class = "c1" > # global branch< / span >
< span class = "n" > x1< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > inception1< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > )< / span >
< span class = "n" > x1_attn< / span > < span class = "p" > ,< / span > < span class = "n" > x1_theta< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > ha1< / span > < span class = "p" > (< / span > < span class = "n" > x1< / span > < span class = "p" > )< / span >
< span class = "n" > x1_out< / span > < span class = "o" > =< / span > < span class = "n" > x1< / span > < span class = "o" > *< / span > < span class = "n" > x1_attn< / span >
< span class = "c1" > # local branch< / span >
< span class = "k" > if< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > learn_region< / span > < span class = "p" > :< / span >
< span class = "n" > x1_local_list< / span > < span class = "o" > =< / span > < span class = "p" > []< / span >
< span class = "k" > for< / span > < span class = "n" > region_idx< / span > < span class = "ow" > in< / span > < span class = "nb" > range< / span > < span class = "p" > (< / span > < span class = "mi" > 4< / span > < span class = "p" > ):< / span >
< span class = "n" > x1_theta_i< / span > < span class = "o" > =< / span > < span class = "n" > x1_theta< / span > < span class = "p" > [:,< / span > < span class = "n" > region_idx< / span > < span class = "p" > ,:]< / span >
< span class = "n" > x1_theta_i< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > transform_theta< / span > < span class = "p" > (< / span > < span class = "n" > x1_theta_i< / span > < span class = "p" > ,< / span > < span class = "n" > region_idx< / span > < span class = "p" > )< / span >
< span class = "n" > x1_trans_i< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stn< / span > < span class = "p" > (< / span > < span class = "n" > x< / span > < span class = "p" > ,< / span > < span class = "n" > x1_theta_i< / span > < span class = "p" > )< / span >
< span class = "n" > x1_trans_i< / span > < span class = "o" > =< / span > < span class = "n" > F< / span > < span class = "o" > .< / span > < span class = "n" > upsample< / span > < span class = "p" > (< / span > < span class = "n" > x1_trans_i< / span > < span class = "p" > ,< / span > < span class = "p" > (< / span > < span class = "mi" > 24< / span > < span class = "p" > ,< / span > < span class = "mi" > 28< / span > < span class = "p" > ),< / span > < span class = "n" > mode< / span > < span class = "o" > =< / span > < span class = "s1" > ' bilinear' < / span > < span class = "p" > ,< / span > < span class = "n" > align_corners< / span > < span class = "o" > =< / span > < span class = "kc" > True< / span > < span class = "p" > )< / span >
< span class = "n" > x1_local_i< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > local_conv1< / span > < span class = "p" > (< / span > < span class = "n" > x1_trans_i< / span > < span class = "p" > )< / span >
< span class = "n" > x1_local_list< / span > < span class = "o" > .< / span > < span class = "n" > append< / span > < span class = "p" > (< / span > < span class = "n" > x1_local_i< / span > < span class = "p" > )< / span >
< span class = "c1" > # ============== Block 2 ==============< / span >
< span class = "c1" > # Block 2< / span >
< span class = "c1" > # global branch< / span >
< span class = "n" > x2< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > inception2< / span > < span class = "p" > (< / span > < span class = "n" > x1_out< / span > < span class = "p" > )< / span >
< span class = "n" > x2_attn< / span > < span class = "p" > ,< / span > < span class = "n" > x2_theta< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > ha2< / span > < span class = "p" > (< / span > < span class = "n" > x2< / span > < span class = "p" > )< / span >
< span class = "n" > x2_out< / span > < span class = "o" > =< / span > < span class = "n" > x2< / span > < span class = "o" > *< / span > < span class = "n" > x2_attn< / span >
< span class = "c1" > # local branch< / span >
< span class = "k" > if< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > learn_region< / span > < span class = "p" > :< / span >
< span class = "n" > x2_local_list< / span > < span class = "o" > =< / span > < span class = "p" > []< / span >
< span class = "k" > for< / span > < span class = "n" > region_idx< / span > < span class = "ow" > in< / span > < span class = "nb" > range< / span > < span class = "p" > (< / span > < span class = "mi" > 4< / span > < span class = "p" > ):< / span >
< span class = "n" > x2_theta_i< / span > < span class = "o" > =< / span > < span class = "n" > x2_theta< / span > < span class = "p" > [:,< / span > < span class = "n" > region_idx< / span > < span class = "p" > ,:]< / span >
< span class = "n" > x2_theta_i< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > transform_theta< / span > < span class = "p" > (< / span > < span class = "n" > x2_theta_i< / span > < span class = "p" > ,< / span > < span class = "n" > region_idx< / span > < span class = "p" > )< / span >
< span class = "n" > x2_trans_i< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stn< / span > < span class = "p" > (< / span > < span class = "n" > x1_out< / span > < span class = "p" > ,< / span > < span class = "n" > x2_theta_i< / span > < span class = "p" > )< / span >
< span class = "n" > x2_trans_i< / span > < span class = "o" > =< / span > < span class = "n" > F< / span > < span class = "o" > .< / span > < span class = "n" > upsample< / span > < span class = "p" > (< / span > < span class = "n" > x2_trans_i< / span > < span class = "p" > ,< / span > < span class = "p" > (< / span > < span class = "mi" > 12< / span > < span class = "p" > ,< / span > < span class = "mi" > 14< / span > < span class = "p" > ),< / span > < span class = "n" > mode< / span > < span class = "o" > =< / span > < span class = "s1" > ' bilinear' < / span > < span class = "p" > ,< / span > < span class = "n" > align_corners< / span > < span class = "o" > =< / span > < span class = "kc" > True< / span > < span class = "p" > )< / span >
< span class = "n" > x2_local_i< / span > < span class = "o" > =< / span > < span class = "n" > x2_trans_i< / span > < span class = "o" > +< / span > < span class = "n" > x1_local_list< / span > < span class = "p" > [< / span > < span class = "n" > region_idx< / span > < span class = "p" > ]< / span >
< span class = "n" > x2_local_i< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > local_conv2< / span > < span class = "p" > (< / span > < span class = "n" > x2_local_i< / span > < span class = "p" > )< / span >
< span class = "n" > x2_local_list< / span > < span class = "o" > .< / span > < span class = "n" > append< / span > < span class = "p" > (< / span > < span class = "n" > x2_local_i< / span > < span class = "p" > )< / span >
< span class = "c1" > # ============== Block 3 ==============< / span >
< span class = "c1" > # Block 3< / span >
< span class = "c1" > # global branch< / span >
< span class = "n" > x3< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > inception3< / span > < span class = "p" > (< / span > < span class = "n" > x2_out< / span > < span class = "p" > )< / span >
< span class = "n" > x3_attn< / span > < span class = "p" > ,< / span > < span class = "n" > x3_theta< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > ha3< / span > < span class = "p" > (< / span > < span class = "n" > x3< / span > < span class = "p" > )< / span >
< span class = "n" > x3_out< / span > < span class = "o" > =< / span > < span class = "n" > x3< / span > < span class = "o" > *< / span > < span class = "n" > x3_attn< / span >
< span class = "c1" > # local branch< / span >
< span class = "k" > if< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > learn_region< / span > < span class = "p" > :< / span >
< span class = "n" > x3_local_list< / span > < span class = "o" > =< / span > < span class = "p" > []< / span >
< span class = "k" > for< / span > < span class = "n" > region_idx< / span > < span class = "ow" > in< / span > < span class = "nb" > range< / span > < span class = "p" > (< / span > < span class = "mi" > 4< / span > < span class = "p" > ):< / span >
< span class = "n" > x3_theta_i< / span > < span class = "o" > =< / span > < span class = "n" > x3_theta< / span > < span class = "p" > [:,< / span > < span class = "n" > region_idx< / span > < span class = "p" > ,:]< / span >
< span class = "n" > x3_theta_i< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > transform_theta< / span > < span class = "p" > (< / span > < span class = "n" > x3_theta_i< / span > < span class = "p" > ,< / span > < span class = "n" > region_idx< / span > < span class = "p" > )< / span >
< span class = "n" > x3_trans_i< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > stn< / span > < span class = "p" > (< / span > < span class = "n" > x2_out< / span > < span class = "p" > ,< / span > < span class = "n" > x3_theta_i< / span > < span class = "p" > )< / span >
< span class = "n" > x3_trans_i< / span > < span class = "o" > =< / span > < span class = "n" > F< / span > < span class = "o" > .< / span > < span class = "n" > upsample< / span > < span class = "p" > (< / span > < span class = "n" > x3_trans_i< / span > < span class = "p" > ,< / span > < span class = "p" > (< / span > < span class = "mi" > 6< / span > < span class = "p" > ,< / span > < span class = "mi" > 7< / span > < span class = "p" > ),< / span > < span class = "n" > mode< / span > < span class = "o" > =< / span > < span class = "s1" > ' bilinear' < / span > < span class = "p" > ,< / span > < span class = "n" > align_corners< / span > < span class = "o" > =< / span > < span class = "kc" > True< / span > < span class = "p" > )< / span >
< span class = "n" > x3_local_i< / span > < span class = "o" > =< / span > < span class = "n" > x3_trans_i< / span > < span class = "o" > +< / span > < span class = "n" > x2_local_list< / span > < span class = "p" > [< / span > < span class = "n" > region_idx< / span > < span class = "p" > ]< / span >
< span class = "n" > x3_local_i< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > local_conv3< / span > < span class = "p" > (< / span > < span class = "n" > x3_local_i< / span > < span class = "p" > )< / span >
< span class = "n" > x3_local_list< / span > < span class = "o" > .< / span > < span class = "n" > append< / span > < span class = "p" > (< / span > < span class = "n" > x3_local_i< / span > < span class = "p" > )< / span >
< span class = "c1" > # ============== Feature generation ==============< / span >
< span class = "c1" > # global branch< / span >
< span class = "n" > x_global< / span > < span class = "o" > =< / span > < span class = "n" > F< / span > < span class = "o" > .< / span > < span class = "n" > avg_pool2d< / span > < span class = "p" > (< / span > < span class = "n" > x3_out< / span > < span class = "p" > ,< / span > < span class = "n" > x3_out< / span > < span class = "o" > .< / span > < span class = "n" > size< / span > < span class = "p" > ()[< / span > < span class = "mi" > 2< / span > < span class = "p" > :])< / span > < span class = "o" > .< / span > < span class = "n" > view< / span > < span class = "p" > (< / span > < span class = "n" > x3_out< / 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 = "n" > x3_out< / span > < span class = "o" > .< / span > < span class = "n" > size< / span > < span class = "p" > (< / span > < span class = "mi" > 1< / span > < span class = "p" > ))< / span >
< span class = "n" > x_global< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > fc_global< / span > < span class = "p" > (< / span > < span class = "n" > x_global< / span > < span class = "p" > )< / span >
< span class = "c1" > # local branch< / span >
< span class = "k" > if< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > learn_region< / span > < span class = "p" > :< / span >
< span class = "n" > x_local_list< / span > < span class = "o" > =< / span > < span class = "p" > []< / span >
< span class = "k" > for< / span > < span class = "n" > region_idx< / span > < span class = "ow" > in< / span > < span class = "nb" > range< / span > < span class = "p" > (< / span > < span class = "mi" > 4< / span > < span class = "p" > ):< / span >
< span class = "n" > x_local_i< / span > < span class = "o" > =< / span > < span class = "n" > x3_local_list< / span > < span class = "p" > [< / span > < span class = "n" > region_idx< / span > < span class = "p" > ]< / span >
< span class = "n" > x_local_i< / span > < span class = "o" > =< / span > < span class = "n" > F< / span > < span class = "o" > .< / span > < span class = "n" > avg_pool2d< / span > < span class = "p" > (< / span > < span class = "n" > x_local_i< / span > < span class = "p" > ,< / span > < span class = "n" > x_local_i< / span > < span class = "o" > .< / span > < span class = "n" > size< / span > < span class = "p" > ()[< / span > < span class = "mi" > 2< / span > < span class = "p" > :])< / span > < span class = "o" > .< / span > < span class = "n" > view< / span > < span class = "p" > (< / span > < span class = "n" > x_local_i< / 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 = "o" > -< / span > < span class = "mi" > 1< / span > < span class = "p" > )< / span >
< span class = "n" > x_local_list< / span > < span class = "o" > .< / span > < span class = "n" > append< / span > < span class = "p" > (< / span > < span class = "n" > x_local_i< / span > < span class = "p" > )< / span >
< span class = "n" > x_local< / span > < span class = "o" > =< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > cat< / span > < span class = "p" > (< / span > < span class = "n" > x_local_list< / span > < span class = "p" > ,< / span > < span class = "mi" > 1< / span > < span class = "p" > )< / span >
< span class = "n" > x_local< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > fc_local< / span > < span class = "p" > (< / span > < span class = "n" > x_local< / span > < span class = "p" > )< / span >
< span class = "k" > if< / span > < span class = "ow" > not< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > training< / span > < span class = "p" > :< / span >
< span class = "c1" > # l2 normalization before concatenation< / span >
< span class = "k" > if< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > learn_region< / span > < span class = "p" > :< / span >
< span class = "n" > x_global< / span > < span class = "o" > =< / span > < span class = "n" > x_global< / span > < span class = "o" > /< / span > < span class = "n" > x_global< / span > < span class = "o" > .< / span > < span class = "n" > norm< / span > < span class = "p" > (< / span > < span class = "n" > p< / span > < span class = "o" > =< / span > < span class = "mi" > 2< / span > < span class = "p" > ,< / span > < span class = "n" > dim< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > ,< / span > < span class = "n" > keepdim< / span > < span class = "o" > =< / span > < span class = "kc" > True< / span > < span class = "p" > )< / span >
< span class = "n" > x_local< / span > < span class = "o" > =< / span > < span class = "n" > x_local< / span > < span class = "o" > /< / span > < span class = "n" > x_local< / span > < span class = "o" > .< / span > < span class = "n" > norm< / span > < span class = "p" > (< / span > < span class = "n" > p< / span > < span class = "o" > =< / span > < span class = "mi" > 2< / span > < span class = "p" > ,< / span > < span class = "n" > dim< / span > < span class = "o" > =< / span > < span class = "mi" > 1< / span > < span class = "p" > ,< / span > < span class = "n" > keepdim< / span > < span class = "o" > =< / span > < span class = "kc" > True< / span > < span class = "p" > )< / span >
< span class = "k" > return< / span > < span class = "n" > torch< / span > < span class = "o" > .< / span > < span class = "n" > cat< / span > < span class = "p" > ([< / span > < span class = "n" > x_global< / span > < span class = "p" > ,< / span > < span class = "n" > x_local< / span > < span class = "p" > ],< / span > < span class = "mi" > 1< / span > < span class = "p" > )< / span >
< span class = "k" > else< / span > < span class = "p" > :< / span >
< span class = "k" > return< / span > < span class = "n" > x_global< / span >
< span class = "n" > prelogits_global< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > classifier_global< / span > < span class = "p" > (< / span > < span class = "n" > x_global< / span > < span class = "p" > )< / span >
< span class = "k" > if< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > learn_region< / span > < span class = "p" > :< / span >
< span class = "n" > prelogits_local< / span > < span class = "o" > =< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > classifier_local< / span > < span class = "p" > (< / span > < span class = "n" > x_local< / span > < span class = "p" > )< / span >
< span class = "k" > if< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > loss< / span > < span class = "o" > ==< / span > < span class = "s1" > ' softmax' < / span > < span class = "p" > :< / span >
< span class = "k" > if< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > learn_region< / span > < span class = "p" > :< / span >
< span class = "k" > return< / span > < span class = "p" > (< / span > < span class = "n" > prelogits_global< / span > < span class = "p" > ,< / span > < span class = "n" > prelogits_local< / span > < span class = "p" > )< / span >
< span class = "k" > else< / span > < span class = "p" > :< / span >
< span class = "k" > return< / span > < span class = "n" > prelogits_global< / span >
< span class = "k" > elif< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > loss< / span > < span class = "o" > ==< / span > < span class = "s1" > ' triplet' < / span > < span class = "p" > :< / span >
< span class = "k" > if< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > learn_region< / span > < span class = "p" > :< / span >
< span class = "k" > return< / span > < span class = "p" > (< / span > < span class = "n" > prelogits_global< / span > < span class = "p" > ,< / span > < span class = "n" > prelogits_local< / span > < span class = "p" > ),< / span > < span class = "p" > (< / span > < span class = "n" > x_global< / span > < span class = "p" > ,< / span > < span class = "n" > x_local< / span > < span class = "p" > )< / span >
< span class = "k" > else< / span > < span class = "p" > :< / span >
< span class = "k" > return< / span > < span class = "n" > prelogits_global< / span > < span class = "p" > ,< / span > < span class = "n" > x_global< / span >
< span class = "k" > else< / span > < span class = "p" > :< / span >
< span class = "k" > raise< / span > < span class = "ne" > KeyError< / span > < span class = "p" > (< / span > < span class = "s2" > " Unsupported loss: < / span > < span class = "si" > {}< / span > < span class = "s2" > " < / span > < span class = "o" > .< / span > < span class = "n" > format< / span > < span class = "p" > (< / span > < span class = "bp" > self< / span > < span class = "o" > .< / span > < span class = "n" > loss< / span > < span class = "p" > ))< / span > < / div >
< / pre > < / div >
< / div >
< / div >
< footer >
< hr / >
< div role = "contentinfo" >
< p >
© Copyright 2019, Kaiyang Zhou
< / p >
< / div >
Built with < a href = "http://sphinx-doc.org/" > Sphinx< / a > using a < a href = "https://github.com/rtfd/sphinx_rtd_theme" > theme< / a > provided by < a href = "https://readthedocs.org" > Read the Docs< / a > .
< / footer >
< / div >
< / div >
< / section >
< / div >
< script type = "text/javascript" >
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
< / script >
< / body >
< / html >