2019-12-21 01:11:46 +00:00
<!DOCTYPE html>
2020-08-13 02:12:50 +00:00
< html lang = "en" >
2019-12-21 01:11:46 +00:00
< head >
< meta charset = "utf-8" / >
2023-01-21 18:34:16 +00:00
< meta name = "viewport" content = "width=device-width, initial-scale=1.0" / > < meta name = "generator" content = "Docutils 0.17.1: http://docutils.sourceforge.net/" / >
2022-01-04 17:32:40 +00:00
2022-12-09 23:55:42 +00:00
<!-- Google tag (gtag.js) -->
< script async src = "https://www.googletagmanager.com/gtag/js?id=UA-156955408-1" > < / script >
< script >
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}
gtag('js', new Date());
gtag('config', 'UA-156955408-1');
< / script >
< title > Draw a pipeline — ONNX Runtime 1.14.0 documentation< / title >
2022-01-04 17:32:40 +00:00
< link rel = "stylesheet" type = "text/css" href = "../static/pygments.css" / >
< link rel = "stylesheet" type = "text/css" href = "../static/alabaster.css" / >
2021-02-11 00:34:31 +00:00
< link rel = "stylesheet" type = "text/css" href = "../static/graphviz.css" / >
2022-01-04 17:32:40 +00:00
< link rel = "stylesheet" type = "text/css" href = "../static/sg_gallery.css" / >
< link rel = "stylesheet" type = "text/css" href = "../static/sg_gallery-binder.css" / >
< link rel = "stylesheet" type = "text/css" href = "../static/sg_gallery-dataframe.css" / >
< link rel = "stylesheet" type = "text/css" href = "../static/sg_gallery-rendered-html.css" / >
< script data-url_root = "../" id = "documentation_options" src = "../static/documentation_options.js" > < / script >
2023-01-21 18:34:16 +00:00
< script src = "../static/jquery.js" > < / script >
< script src = "../static/underscore.js" > < / script >
< script src = "../static/_sphinx_javascript_frameworks_compat.js" > < / script >
2021-02-11 00:34:31 +00:00
< script src = "../static/doctools.js" > < / script >
2022-12-09 23:55:42 +00:00
< script src = "../static/sphinx_highlight.js" > < / script >
2019-12-21 01:11:46 +00:00
< link rel = "index" title = "Index" href = "../genindex.html" / >
< link rel = "search" title = "Search" href = "../search.html" / >
< link rel = "next" title = "Load and predict with ONNX Runtime and a very simple model" href = "plot_load_and_predict.html" / >
< link rel = "prev" title = "Gallery of examples" href = "index.html" / >
2021-02-11 00:34:31 +00:00
< link rel = "stylesheet" href = "../static/custom.css" type = "text/css" / >
2019-12-21 01:11:46 +00:00
< meta name = "viewport" content = "width=device-width, initial-scale=0.9, maximum-scale=0.9" / >
< / head > < body >
< div class = "document" >
< div class = "documentwrapper" >
< div class = "bodywrapper" >
< div class = "body" role = "main" >
< div class = "sphx-glr-download-link-note admonition note" >
< p class = "admonition-title" > Note< / p >
2021-03-09 18:21:38 +00:00
< p > Click < a class = "reference internal" href = "#sphx-glr-download-auto-examples-plot-pipeline-py" > < span class = "std std-ref" > here< / span > < / a >
to download the full example code< / p >
2019-12-21 01:11:46 +00:00
< / div >
2022-01-04 17:32:40 +00:00
< section class = "sphx-glr-example-title" id = "draw-a-pipeline" >
2022-08-03 17:24:42 +00:00
< span id = "sphx-glr-auto-examples-plot-pipeline-py" > < / span > < h1 > Draw a pipeline< a class = "headerlink" href = "#draw-a-pipeline" title = "Permalink to this heading" > ¶< / a > < / h1 >
2019-12-21 01:11:46 +00:00
< p > There is no other way to look into one model stored
in ONNX format than looking into its node with
< em > onnx< / em > . This example demonstrates
how to draw a model and to retrieve it in < em > json< / em >
format.< / p >
2023-01-21 18:34:16 +00:00
< div class = "contents local topic" id = "contents" >
2019-12-21 01:11:46 +00:00
< ul class = "simple" >
< li > < p > < a class = "reference internal" href = "#retrieve-a-model-in-json-format" id = "id1" > Retrieve a model in JSON format< / a > < / p > < / li >
< li > < p > < a class = "reference internal" href = "#draw-a-model-with-onnx" id = "id2" > Draw a model with ONNX< / a > < / p > < / li >
< / ul >
2023-01-21 18:34:16 +00:00
< / div >
2022-01-04 17:32:40 +00:00
< section id = "retrieve-a-model-in-json-format" >
2023-01-21 18:34:16 +00:00
< h2 > < a class = "toc-backref" href = "#id1" > Retrieve a model in JSON format< / a > < a class = "headerlink" href = "#retrieve-a-model-in-json-format" title = "Permalink to this heading" > ¶< / a > < / h2 >
2019-12-21 01:11:46 +00:00
< p > That’ < / p >
2022-12-09 23:55:42 +00:00
< div class = "highlight-default notranslate" > < div class = "highlight" > < pre > < span > < / span > < span class = "kn" > from< / span > < span class = "nn" > onnxruntime.datasets< / span > < span class = "kn" > import< / span > < span class = "n" > get_example< / span >
2022-08-03 17:24:42 +00:00
2019-12-21 01:11:46 +00:00
< span class = "n" > example1< / span > < span class = "o" > =< / span > < span class = "n" > get_example< / span > < span class = "p" > (< / span > < span class = "s2" > " mul_1.onnx" < / span > < span class = "p" > )< / span >
< span class = "kn" > import< / span > < span class = "nn" > onnx< / span >
2022-08-03 17:24:42 +00:00
2019-12-21 01:11:46 +00:00
< span class = "n" > model< / span > < span class = "o" > =< / span > < span class = "n" > onnx< / span > < span class = "o" > .< / span > < span class = "n" > load< / span > < span class = "p" > (< / span > < span class = "n" > example1< / span > < span class = "p" > )< / span > < span class = "c1" > # model is a ModelProto protobuf message< / span >
2020-08-13 02:12:50 +00:00
< span class = "nb" > print< / span > < span class = "p" > (< / span > < span class = "n" > model< / span > < span class = "p" > )< / span >
2019-12-21 01:11:46 +00:00
< / pre > < / div >
< / div >
2021-02-11 00:34:31 +00:00
< div class = "sphx-glr-script-out highlight-none notranslate" > < div class = "highlight" > < pre > < span > < / span > ir_version: 3
producer_name: " chenta"
2019-12-21 01:11:46 +00:00
graph {
node {
input: " X"
input: " W"
output: " Y"
name: " mul_1"
op_type: " Mul"
}
name: " mul test"
initializer {
dims: 3
dims: 2
data_type: 1
float_data: 1.0
float_data: 2.0
float_data: 3.0
float_data: 4.0
float_data: 5.0
float_data: 6.0
name: " W"
}
input {
name: " X"
type {
tensor_type {
elem_type: 1
shape {
dim {
dim_value: 3
}
dim {
dim_value: 2
}
}
}
}
}
output {
name: " Y"
type {
tensor_type {
elem_type: 1
shape {
dim {
dim_value: 3
}
dim {
dim_value: 2
}
}
}
}
}
}
opset_import {
domain: " "
version: 7
}
< / pre > < / div >
< / div >
2022-01-04 17:32:40 +00:00
< / section >
< section id = "draw-a-model-with-onnx" >
2023-01-21 18:34:16 +00:00
< h2 > < a class = "toc-backref" href = "#id2" > Draw a model with ONNX< / a > < a class = "headerlink" href = "#draw-a-model-with-onnx" title = "Permalink to this heading" > ¶< / a > < / h2 >
2022-12-09 23:55:42 +00:00
< p > We use < a class = "reference external" href = "https://github.com/onnx/onnx/blob/main/onnx/tools/net_drawer.py" > net_drawer.py< / a >
2019-12-21 01:11:46 +00:00
included in < em > onnx< / em > package.
We use < em > onnx< / em > to load the model
in a different way than before.< / p >
2022-12-09 23:55:42 +00:00
< div class = "highlight-default notranslate" > < div class = "highlight" > < pre > < span > < / span > < span class = "kn" > from< / span > < span class = "nn" > onnx< / span > < span class = "kn" > import< / span > < span class = "n" > ModelProto< / span >
2022-08-03 17:24:42 +00:00
2019-12-21 01:11:46 +00:00
< span class = "n" > model< / span > < span class = "o" > =< / span > < span class = "n" > ModelProto< / span > < span class = "p" > ()< / span >
2022-08-03 17:24:42 +00:00
< span class = "k" > with< / span > < span class = "nb" > open< / span > < span class = "p" > (< / span > < span class = "n" > example1< / span > < span class = "p" > ,< / span > < span class = "s2" > " rb" < / span > < span class = "p" > )< / span > < span class = "k" > as< / span > < span class = "n" > fid< / span > < span class = "p" > :< / span >
2019-12-21 01:11:46 +00:00
< span class = "n" > content< / span > < span class = "o" > =< / span > < span class = "n" > fid< / span > < span class = "o" > .< / span > < span class = "n" > read< / span > < span class = "p" > ()< / span >
< span class = "n" > model< / span > < span class = "o" > .< / span > < span class = "n" > ParseFromString< / span > < span class = "p" > (< / span > < span class = "n" > content< / span > < span class = "p" > )< / span >
< / pre > < / div >
< / div >
< p > We convert it into a graph.< / p >
2022-12-09 23:55:42 +00:00
< div class = "highlight-default notranslate" > < div class = "highlight" > < pre > < span > < / span > < span class = "kn" > from< / span > < span class = "nn" > onnx.tools.net_drawer< / span > < span class = "kn" > import< / span > < span class = "n" > GetOpNodeProducer< / span > < span class = "p" > ,< / span > < span class = "n" > GetPydotGraph< / span >
2022-08-03 17:24:42 +00:00
< span class = "n" > pydot_graph< / span > < span class = "o" > =< / span > < span class = "n" > GetPydotGraph< / span > < span class = "p" > (< / span >
< span class = "n" > model< / span > < span class = "o" > .< / span > < span class = "n" > graph< / span > < span class = "p" > ,< / span > < span class = "n" > name< / span > < span class = "o" > =< / span > < span class = "n" > model< / span > < span class = "o" > .< / span > < span class = "n" > graph< / span > < span class = "o" > .< / span > < span class = "n" > name< / span > < span class = "p" > ,< / span > < span class = "n" > rankdir< / span > < span class = "o" > =< / span > < span class = "s2" > " LR" < / span > < span class = "p" > ,< / span > < span class = "n" > node_producer< / span > < span class = "o" > =< / span > < span class = "n" > GetOpNodeProducer< / span > < span class = "p" > (< / span > < span class = "s2" > " docstring" < / span > < span class = "p" > )< / span >
< span class = "p" > )< / span >
2019-12-21 01:11:46 +00:00
< span class = "n" > pydot_graph< / span > < span class = "o" > .< / span > < span class = "n" > write_dot< / span > < span class = "p" > (< / span > < span class = "s2" > " graph.dot" < / span > < span class = "p" > )< / span >
< / pre > < / div >
< / div >
< p > Then into an image< / p >
2020-08-13 02:12:50 +00:00
< div class = "highlight-default notranslate" > < div class = "highlight" > < pre > < span > < / span > < span class = "kn" > import< / span > < span class = "nn" > os< / span >
2022-08-03 17:24:42 +00:00
< span class = "n" > os< / span > < span class = "o" > .< / span > < span class = "n" > system< / span > < span class = "p" > (< / span > < span class = "s2" > " dot -O -Tpng graph.dot" < / span > < span class = "p" > )< / span >
2019-12-21 01:11:46 +00:00
< / pre > < / div >
< / div >
2020-08-13 02:12:50 +00:00
< div class = "sphx-glr-script-out highlight-none notranslate" > < div class = "highlight" > < pre > < span > < / span > 0
< / pre > < / div >
< / div >
2019-12-21 01:11:46 +00:00
< p > Which we display…< / p >
2020-08-13 02:12:50 +00:00
< div class = "highlight-default notranslate" > < div class = "highlight" > < pre > < span > < / span > < span class = "kn" > import< / span > < span class = "nn" > matplotlib.pyplot< / span > < span class = "k" > as< / span > < span class = "nn" > plt< / span >
2022-08-03 17:24:42 +00:00
2019-12-21 01:11:46 +00:00
< span class = "n" > image< / span > < span class = "o" > =< / span > < span class = "n" > plt< / span > < span class = "o" > .< / span > < span class = "n" > imread< / span > < span class = "p" > (< / span > < span class = "s2" > " graph.dot.png" < / span > < span class = "p" > )< / span >
< span class = "n" > plt< / span > < span class = "o" > .< / span > < span class = "n" > imshow< / span > < span class = "p" > (< / span > < span class = "n" > image< / span > < span class = "p" > )< / span >
< / pre > < / div >
< / div >
2023-01-26 23:29:00 +00:00
< img src = "../images/sphx_glr_plot_pipeline_001.png" srcset = "../images/sphx_glr_plot_pipeline_001.png" alt = "plot pipeline" class = "sphx-glr-single-img" / > < div class = "sphx-glr-script-out highlight-none notranslate" > < div class = "highlight" > < pre > < span > < / span > < matplotlib.image.AxesImage object at 0x7f0fecf2bd90>
2020-08-13 02:12:50 +00:00
< / pre > < / div >
< / div >
2023-01-26 23:29:00 +00:00
< p class = "sphx-glr-timing" > < strong > Total running time of the script:< / strong > ( 0 minutes 0.136 seconds)< / p >
2022-08-03 17:24:42 +00:00
< div class = "sphx-glr-footer sphx-glr-footer-example docutils container" id = "sphx-glr-download-auto-examples-plot-pipeline-py" >
2020-08-13 02:12:50 +00:00
< div class = "sphx-glr-download sphx-glr-download-python docutils container" >
2021-03-09 18:21:38 +00:00
< p > < a class = "reference download internal" download = "" href = "../downloads/d436e9922b51a71358604ec00f09e7e4/plot_pipeline.py" > < code class = "xref download docutils literal notranslate" > < span class = "pre" > Download< / span > < span class = "pre" > Python< / span > < span class = "pre" > source< / span > < span class = "pre" > code:< / span > < span class = "pre" > plot_pipeline.py< / span > < / code > < / a > < / p >
2019-12-21 01:11:46 +00:00
< / div >
2020-08-13 02:12:50 +00:00
< div class = "sphx-glr-download sphx-glr-download-jupyter docutils container" >
2021-03-09 18:21:38 +00:00
< p > < a class = "reference download internal" download = "" href = "../downloads/2dbd202de70c8b6a394b8a1c7c1e12b8/plot_pipeline.ipynb" > < code class = "xref download docutils literal notranslate" > < span class = "pre" > Download< / span > < span class = "pre" > Jupyter< / span > < span class = "pre" > notebook:< / span > < span class = "pre" > plot_pipeline.ipynb< / span > < / code > < / a > < / p >
2019-12-21 01:11:46 +00:00
< / div >
< / div >
2020-08-13 02:12:50 +00:00
< p class = "sphx-glr-signature" > < a class = "reference external" href = "https://sphinx-gallery.github.io" > Gallery generated by Sphinx-Gallery< / a > < / p >
2022-01-04 17:32:40 +00:00
< / section >
< / section >
2019-12-21 01:11:46 +00:00
< / div >
< / div >
< / div >
< div class = "sphinxsidebar" role = "navigation" aria-label = "main navigation" >
< div class = "sphinxsidebarwrapper" >
< p class = "logo" > < a href = "../index.html" >
2021-02-11 00:34:31 +00:00
< img class = "logo" src = "../static/ONNX_Runtime_icon.png" alt = "Logo" / >
2019-12-21 01:11:46 +00:00
< / a > < / p >
< h1 class = "logo" > < a href = "../index.html" > ONNX Runtime< / a > < / h1 >
< h3 > Navigation< / h3 >
2021-03-09 18:21:38 +00:00
< ul >
2019-12-21 01:11:46 +00:00
< li class = "toctree-l1" > < a class = "reference internal" href = "../tutorial.html" > Tutorial< / a > < / li >
2022-03-16 01:13:11 +00:00
< li class = "toctree-l1" > < a class = "reference internal" href = "../api_summary.html" > API< / a > < / li >
2021-03-09 18:21:38 +00:00
< li class = "toctree-l1" > < a class = "reference internal" href = "index.html" > Gallery of examples< / a > < / li >
2019-12-21 01:11:46 +00:00
< / ul >
< div class = "relations" >
< h3 > Related Topics< / h3 >
< ul >
< li > < a href = "../index.html" > Documentation overview< / a > < ul >
< li > < a href = "index.html" > Gallery of examples< / a > < ul >
< li > Previous: < a href = "index.html" title = "previous chapter" > Gallery of examples< / a > < / li >
< li > Next: < a href = "plot_load_and_predict.html" title = "next chapter" > Load and predict with ONNX Runtime and a very simple model< / a > < / li >
< / ul > < / li >
< / ul > < / li >
< / ul >
< / div >
< div id = "searchbox" style = "display: none" role = "search" >
< h3 id = "searchlabel" > Quick search< / h3 >
< div class = "searchformwrapper" >
< form class = "search" action = "../search.html" method = "get" >
2022-01-04 17:32:40 +00:00
< input type = "text" name = "q" aria-labelledby = "searchlabel" autocomplete = "off" autocorrect = "off" autocapitalize = "off" spellcheck = "false" / >
2019-12-21 01:11:46 +00:00
< input type = "submit" value = "Go" / >
< / form >
< / div >
< / div >
2022-08-03 17:24:42 +00:00
< script > document . getElementById ( 'searchbox' ) . style . display = "block" < / script >
2020-04-06 22:52:48 +00:00
2019-12-21 01:11:46 +00:00
< / div >
< / div >
< div class = "clearer" > < / div >
< / div >
< div class = "footer" >
2023-01-21 18:34:16 +00:00
© 2018-2023, Microsoft.
2019-12-21 01:11:46 +00:00
|
2023-01-21 18:34:16 +00:00
Powered by < a href = "http://sphinx-doc.org/" > Sphinx 5.3.0< / a >
2023-01-20 00:19:31 +00:00
& < a href = "https://github.com/bitprophet/alabaster" > Alabaster 0.7.13< / a >
2019-12-21 01:11:46 +00:00
|
2021-02-11 00:34:31 +00:00
< a href = "../sources/auto_examples/plot_pipeline.rst.txt"
2019-12-21 01:11:46 +00:00
rel="nofollow">Page source< / a >
< / div >
< / body >
< / html >
