2019-10-30 16:35:16 +00:00
<!DOCTYPE html>
2019-12-20 21:35:58 +00:00
< html lang = "en" >
< head >
< meta charset = "utf-8" >
< meta name = "viewport" content = "width=device-width, initial-scale=1, shrink-to-fit=no" >
< meta http-equiv = "x-ua-compatible" content = "ie=edge" >
< title > ONNX Runtime for Keras< / title >
< link rel = "stylesheet" href = "../_static/pyramid.css" type = "text/css" / >
< link rel = "stylesheet" href = "../_static/pygments.css" type = "text/css" / >
< link rel = "stylesheet" href = "../_static/gallery.css" type = "text/css" / >
< / head >
< body >
< div class = "container" >
< div class = "row" style = "margin-top: 1rem;" >
< div id = "sidebar" class = "col-xs-12 col-sm-3" >
< a href = "../index.html" >
< img style = "margin-bottom: 0.5rem;" class = "img-fluid" src = "../_static/ONNX_Runtime_icon.png" / >
< / a >
< div id = "searchbox" style = "display: none" role = "search" >
< form class = "form-inline" action = "../search.html" method = "get" >
< div class = "form-group" >
< label class = "sr-only" for = "searchInput" > Search< / label >
< input type = "text" class = "form-control" name = "q" id = "searchInput" placeholder = "Search" >
< / div >
< button type = "submit" class = "btn btn-secondary" style = "display:none" > Go< / button >
< input type = "hidden" name = "check_keywords" value = "yes" / >
< input type = "hidden" name = "area" value = "default" / >
< / form >
< / div >
2019-10-30 16:35:16 +00:00
2019-12-20 21:35:58 +00:00
< hr >
2019-10-30 16:35:16 +00:00
2019-12-20 21:35:58 +00:00
< div id = "toc" >
< ul class = "current" >
< li class = "toctree-l1" > < a class = "reference internal" href = "../tutorial.html" > Tutorial< / a > < ul >
< li class = "toctree-l2" > < a class = "reference internal" href = "../tutorial.html#step-1-train-a-model-using-your-favorite-framework" > Step 1: Train a model using your favorite framework< / a > < / li >
< li class = "toctree-l2" > < a class = "reference internal" href = "../tutorial.html#step-2-convert-or-export-the-model-into-onnx-format" > Step 2: Convert or export the model into ONNX format< / a > < / li >
< li class = "toctree-l2" > < a class = "reference internal" href = "../tutorial.html#step-3-load-and-run-the-model-using-onnx-runtime" > Step 3: Load and run the model using ONNX Runtime< / a > < / li >
< / ul >
< / li >
< li class = "toctree-l1" > < a class = "reference internal" href = "../api_summary.html" > API Summary< / a > < ul >
< li class = "toctree-l2" > < a class = "reference internal" href = "../api_summary.html#device" > Device< / a > < / li >
< li class = "toctree-l2" > < a class = "reference internal" href = "../api_summary.html#examples-and-datasets" > Examples and datasets< / a > < / li >
< li class = "toctree-l2" > < a class = "reference internal" href = "../api_summary.html#load-and-run-a-model" > Load and run a model< / a > < / li >
< li class = "toctree-l2" > < a class = "reference internal" href = "../api_summary.html#backend" > Backend< / a > < / li >
< / ul >
< / li >
< li class = "toctree-l1 current" > < a class = "reference internal" href = "index.html" > Gallery of examples< / a > < ul class = "current" >
< li class = "toctree-l2" > < a class = "reference internal" href = "plot_pipeline.html" > Draw a pipeline< / a > < / li >
< li class = "toctree-l2" > < a class = "reference internal" href = "plot_load_and_predict.html" > Load and predict with ONNX Runtime and a very simple model< / a > < / li >
< li class = "toctree-l2" > < a class = "reference internal" href = "plot_profiling.html" > Profile the execution of a simple model< / a > < / li >
< li class = "toctree-l2" > < a class = "reference internal" href = "plot_backend.html" > ONNX Runtime Backend for ONNX< / a > < / li >
< li class = "toctree-l2" > < a class = "reference internal" href = "plot_metadata.html" > Metadata< / a > < / li >
< li class = "toctree-l2 current" > < a class = "current reference internal" href = "#" > ONNX Runtime for Keras< / a > < / li >
< li class = "toctree-l2" > < a class = "reference internal" href = "plot_convert_pipeline_vectorizer.html" > Train, convert and predict with ONNX Runtime< / a > < / li >
< li class = "toctree-l2" > < a class = "reference internal" href = "plot_common_errors.html" > Common errors with onnxruntime< / a > < / li >
< li class = "toctree-l2" > < a class = "reference internal" href = "plot_train_convert_predict.html" > Train, convert and predict with ONNX Runtime< / a > < / li >
< / ul >
< / li >
< / ul >
2019-10-30 16:35:16 +00:00
2019-12-20 21:35:58 +00:00
< / div >
< / div >
< div class = "col-xs-12 col-sm-9" >
< div class = "sphx-glr-download-link-note admonition note" >
< p class = "first admonition-title" > Note< / p >
< p class = "last" > Click < a class = "reference internal" href = "#sphx-glr-download-auto-examples-plot-dl-keras-py" > < span class = "std std-ref" > here< / span > < / a > to download the full example code< / p >
2019-10-30 16:35:16 +00:00
< / div >
< div class = "sphx-glr-example-title section" id = "onnx-runtime-for-keras" >
< span id = "l-example-backend-api-tensorflow" > < / span > < span id = "sphx-glr-auto-examples-plot-dl-keras-py" > < / span > < h1 > ONNX Runtime for Keras< a class = "headerlink" href = "#onnx-runtime-for-keras" title = "Permalink to this headline" > ¶< / a > < / h1 >
< p > The following demonstrates how to compute the predictions
of a pretrained deep learning model obtained from
< a class = "reference external" href = "https://keras.io/" > keras< / a >
with < em > onnxruntime< / em > . The conversion requires
< a class = "reference external" href = "https://keras.io/" > keras< / a > ,
< a class = "reference external" href = "https://www.tensorflow.org/" > tensorflow< / a > ,
< a class = "reference external" href = "https://github.com/onnx/keras-onnx/" > keras-onnx< / a > ,
< a class = "reference external" href = "https://pypi.org/project/onnxmltools/" > onnxmltools< / a >
but then only < em > onnxruntime< / em > is required
to compute the predictions.< / p >
2019-12-20 21:35:58 +00:00
< div class = "highlight-python notranslate" > < div class = "highlight" > < pre > < span > < / span > < span class = "kn" > import< / span > < span class = "nn" > os< / span >
2019-10-30 16:35:16 +00:00
< span class = "k" > if< / span > < span class = "ow" > not< / span > < span class = "n" > os< / span > < span class = "o" > .< / span > < span class = "n" > path< / span > < span class = "o" > .< / span > < span class = "n" > exists< / span > < span class = "p" > (< / span > < span class = "s1" > ' dense121.onnx' < / span > < span class = "p" > ):< / span >
2019-12-20 21:35:58 +00:00
< span class = "kn" > from< / span > < span class = "nn" > keras.applications.densenet< / span > < span class = "kn" > import< / span > < span class = "n" > DenseNet121< / span >
< span class = "n" > model< / span > < span class = "o" > =< / span > < span class = "n" > DenseNet121< / span > < span class = "p" > (< / span > < span class = "n" > include_top< / span > < span class = "o" > =< / span > < span class = "bp" > True< / span > < span class = "p" > ,< / span > < span class = "n" > weights< / span > < span class = "o" > =< / span > < span class = "s1" > ' imagenet' < / span > < span class = "p" > )< / span >
2019-10-30 16:35:16 +00:00
2019-12-20 21:35:58 +00:00
< span class = "kn" > from< / span > < span class = "nn" > keras2onnx< / span > < span class = "kn" > import< / span > < span class = "n" > convert_keras< / span >
2019-10-30 16:35:16 +00:00
< span class = "n" > onx< / span > < span class = "o" > =< / span > < span class = "n" > convert_keras< / span > < span class = "p" > (< / span > < span class = "n" > model< / span > < span class = "p" > ,< / span > < span class = "s1" > ' dense121.onnx' < / span > < span class = "p" > )< / span >
< span class = "k" > with< / span > < span class = "nb" > open< / span > < span class = "p" > (< / span > < span class = "s2" > " dense121.onnx" < / span > < span class = "p" > ,< / span > < span class = "s2" > " wb" < / span > < span class = "p" > )< / span > < span class = "k" > as< / span > < span class = "n" > f< / span > < span class = "p" > :< / span >
< span class = "n" > f< / span > < span class = "o" > .< / span > < span class = "n" > write< / span > < span class = "p" > (< / span > < span class = "n" > onx< / span > < span class = "o" > .< / span > < span class = "n" > SerializeToString< / span > < span class = "p" > ())< / span >
< / pre > < / div >
< / div >
< p > Let’ < / p >
2019-12-20 21:35:58 +00:00
< div class = "highlight-python notranslate" > < div class = "highlight" > < pre > < span > < / span > < span class = "kn" > from< / span > < span class = "nn" > keras.preprocessing.image< / span > < span class = "kn" > import< / span > < span class = "n" > array_to_img< / span > < span class = "p" > ,< / span > < span class = "n" > img_to_array< / span > < span class = "p" > ,< / span > < span class = "n" > load_img< / span >
2019-10-30 16:35:16 +00:00
< span class = "n" > img< / span > < span class = "o" > =< / span > < span class = "n" > load_img< / span > < span class = "p" > (< / span > < span class = "s1" > ' Sannosawa1.jpg' < / span > < span class = "p" > )< / span >
< span class = "n" > ximg< / span > < span class = "o" > =< / span > < span class = "n" > img_to_array< / span > < span class = "p" > (< / span > < span class = "n" > img< / span > < span class = "p" > )< / span >
2019-12-20 21:35:58 +00:00
< span class = "kn" > import< / span > < span class = "nn" > matplotlib.pyplot< / span > < span class = "kn" > as< / span > < span class = "nn" > plt< / span >
2019-10-30 16:35:16 +00:00
< span class = "n" > plt< / span > < span class = "o" > .< / span > < span class = "n" > imshow< / span > < span class = "p" > (< / span > < span class = "n" > ximg< / span > < span class = "o" > /< / span > < span class = "mi" > 255< / span > < span class = "p" > )< / span >
< span class = "n" > plt< / span > < span class = "o" > .< / span > < span class = "n" > axis< / span > < span class = "p" > (< / span > < span class = "s1" > ' off' < / span > < span class = "p" > )< / span >
< / pre > < / div >
< / div >
< img alt = "../_images/sphx_glr_plot_dl_keras_001.png" class = "sphx-glr-single-img" src = "../_images/sphx_glr_plot_dl_keras_001.png" / >
< p > Let’ < / p >
2019-12-20 21:35:58 +00:00
< div class = "highlight-python notranslate" > < div class = "highlight" > < pre > < span > < / span > < span class = "kn" > import< / span > < span class = "nn" > onnxruntime< / span > < span class = "kn" > as< / span > < span class = "nn" > rt< / span >
< span class = "kn" > from< / span > < span class = "nn" > onnxruntime.capi.onnxruntime_pybind11_state< / span > < span class = "kn" > import< / span > < span class = "n" > InvalidGraph< / span >
2019-10-30 16:35:16 +00:00
< span class = "k" > try< / span > < span class = "p" > :< / span >
< span class = "n" > sess< / span > < span class = "o" > =< / span > < span class = "n" > rt< / span > < span class = "o" > .< / span > < span class = "n" > InferenceSession< / span > < span class = "p" > (< / span > < span class = "s1" > ' dense121.onnx' < / span > < span class = "p" > )< / span >
2019-12-20 21:35:58 +00:00
< span class = "n" > ok< / span > < span class = "o" > =< / span > < span class = "bp" > True< / span >
2019-10-30 16:35:16 +00:00
< span class = "k" > except< / span > < span class = "p" > (< / span > < span class = "n" > InvalidGraph< / span > < span class = "p" > ,< / span > < span class = "ne" > TypeError< / span > < span class = "p" > ,< / span > < span class = "ne" > RuntimeError< / span > < span class = "p" > )< / span > < span class = "k" > as< / span > < span class = "n" > e< / span > < span class = "p" > :< / span >
< span class = "c1" > # Probably a mismatch between onnxruntime and onnx version.< / span >
2019-12-20 21:35:58 +00:00
< span class = "k" > print< / span > < span class = "p" > (< / span > < span class = "n" > e< / span > < span class = "p" > )< / span >
< span class = "n" > ok< / span > < span class = "o" > =< / span > < span class = "bp" > False< / span >
2019-10-30 16:35:16 +00:00
< span class = "k" > if< / span > < span class = "n" > ok< / span > < span class = "p" > :< / span >
2019-12-20 21:35:58 +00:00
< span class = "k" > print< / span > < span class = "p" > (< / span > < span class = "s2" > " The model expects input shape:" < / span > < span class = "p" > ,< / span > < span class = "n" > sess< / span > < span class = "o" > .< / span > < span class = "n" > get_inputs< / span > < span class = "p" > ()[< / span > < span class = "mi" > 0< / span > < span class = "p" > ]< / span > < span class = "o" > .< / span > < span class = "n" > shape< / span > < span class = "p" > )< / span >
< span class = "k" > print< / span > < span class = "p" > (< / span > < span class = "s2" > " image shape:" < / span > < span class = "p" > ,< / span > < span class = "n" > ximg< / span > < span class = "o" > .< / span > < span class = "n" > shape< / span > < span class = "p" > )< / span >
2019-10-30 16:35:16 +00:00
< / pre > < / div >
< / div >
< p class = "sphx-glr-script-out" > Out:< / p >
2019-12-20 21:35:58 +00:00
< div class = "sphx-glr-script-out highlight-none notranslate" > < div class = "highlight" > < pre > < span > < / span > The model expects input shape: [' N' , 224, 224, 3]
2019-10-30 16:35:16 +00:00
image shape: (960, 1280, 3)
< / pre > < / div >
< / div >
< p > Let’ < / p >
2019-12-20 21:35:58 +00:00
< div class = "highlight-python notranslate" > < div class = "highlight" > < pre > < span > < / span > < span class = "k" > if< / span > < span class = "n" > ok< / span > < span class = "p" > :< / span >
< span class = "kn" > from< / span > < span class = "nn" > skimage.transform< / span > < span class = "kn" > import< / span > < span class = "n" > resize< / span >
2019-10-30 16:35:16 +00:00
< span class = "kn" > import< / span > < span class = "nn" > numpy< / span >
2019-12-20 21:35:58 +00:00
< span class = "n" > ximg224< / span > < span class = "o" > =< / span > < span class = "n" > resize< / span > < span class = "p" > (< / span > < span class = "n" > ximg< / span > < span class = "o" > /< / span > < span class = "mi" > 255< / span > < span class = "p" > ,< / span > < span class = "p" > (< / span > < span class = "mi" > 224< / span > < span class = "p" > ,< / span > < span class = "mi" > 224< / span > < span class = "p" > ,< / span > < span class = "mi" > 3< / span > < span class = "p" > ),< / span > < span class = "n" > anti_aliasing< / span > < span class = "o" > =< / span > < span class = "bp" > True< / span > < span class = "p" > )< / span >
2019-10-30 16:35:16 +00:00
< span class = "n" > ximg< / span > < span class = "o" > =< / span > < span class = "n" > ximg224< / span > < span class = "p" > [< / span > < span class = "n" > numpy< / span > < span class = "o" > .< / span > < span class = "n" > newaxis< / span > < span class = "p" > ,< / span > < span class = "p" > :,< / span > < span class = "p" > :,< / span > < span class = "p" > :]< / span >
< span class = "n" > ximg< / span > < span class = "o" > =< / span > < span class = "n" > ximg< / span > < span class = "o" > .< / span > < span class = "n" > astype< / span > < span class = "p" > (< / span > < span class = "n" > numpy< / span > < span class = "o" > .< / span > < span class = "n" > float32< / span > < span class = "p" > )< / span >
2019-12-20 21:35:58 +00:00
< span class = "k" > print< / span > < span class = "p" > (< / span > < span class = "s2" > " new shape:" < / span > < span class = "p" > ,< / span > < span class = "n" > ximg< / span > < span class = "o" > .< / span > < span class = "n" > shape< / span > < span class = "p" > )< / span >
2019-10-30 16:35:16 +00:00
< / pre > < / div >
< / div >
< p class = "sphx-glr-script-out" > Out:< / p >
< div class = "sphx-glr-script-out highlight-none notranslate" > < div class = "highlight" > < pre > < span > < / span > new shape: (1, 224, 224, 3)
< / pre > < / div >
< / div >
< p > Let’ < / p >
2019-12-20 21:35:58 +00:00
< div class = "highlight-python notranslate" > < div class = "highlight" > < pre > < span > < / span > < span class = "k" > if< / span > < span class = "n" > ok< / span > < span class = "p" > :< / span >
2019-10-30 16:35:16 +00:00
< span class = "n" > input_name< / span > < span class = "o" > =< / span > < span class = "n" > sess< / span > < span class = "o" > .< / span > < span class = "n" > get_inputs< / span > < span class = "p" > ()[< / span > < span class = "mi" > 0< / span > < span class = "p" > ]< / span > < span class = "o" > .< / span > < span class = "n" > name< / span >
2019-12-20 21:35:58 +00:00
< span class = "n" > res< / span > < span class = "o" > =< / span > < span class = "n" > sess< / span > < span class = "o" > .< / span > < span class = "n" > run< / span > < span class = "p" > (< / span > < span class = "bp" > None< / span > < span class = "p" > ,< / span > < span class = "p" > {< / span > < span class = "n" > input_name< / span > < span class = "p" > :< / span > < span class = "n" > ximg< / span > < span class = "p" > })< / span >
2019-10-30 16:35:16 +00:00
< span class = "n" > prob< / span > < span class = "o" > =< / span > < span class = "n" > res< / span > < span class = "p" > [< / span > < span class = "mi" > 0< / span > < span class = "p" > ]< / span >
2019-12-20 21:35:58 +00:00
< span class = "k" > print< / span > < span class = "p" > (< / span > < span class = "n" > prob< / span > < span class = "o" > .< / span > < span class = "n" > ravel< / span > < span class = "p" > ()[:< / span > < span class = "mi" > 10< / span > < span class = "p" > ])< / span > < span class = "c1" > # Too big to be displayed.< / span >
2019-10-30 16:35:16 +00:00
< / pre > < / div >
< / div >
< p class = "sphx-glr-script-out" > Out:< / p >
2019-12-20 21:35:58 +00:00
< div class = "sphx-glr-script-out highlight-none notranslate" > < div class = "highlight" > < pre > < span > < / span > [5.3862054e-06 6.1927537e-08 2.0104133e-07 1.3239808e-06 1.0415122e-06
6.7792627e-08 3.1348068e-07 3.2683040e-08 1.0914272e-07 1.1627122e-06]
2019-10-30 16:35:16 +00:00
< / pre > < / div >
< / div >
< p > Let’ < / p >
2019-12-20 21:35:58 +00:00
< div class = "highlight-python notranslate" > < div class = "highlight" > < pre > < span > < / span > < span class = "k" > if< / span > < span class = "n" > ok< / span > < span class = "p" > :< / span >
< span class = "kn" > from< / span > < span class = "nn" > keras.applications.densenet< / span > < span class = "kn" > import< / span > < span class = "n" > decode_predictions< / span >
2019-10-30 16:35:16 +00:00
< span class = "n" > decoded< / span > < span class = "o" > =< / span > < span class = "n" > decode_predictions< / span > < span class = "p" > (< / span > < span class = "n" > prob< / span > < span class = "p" > )< / span >
< span class = "kn" > import< / span > < span class = "nn" > pandas< / span >
< span class = "n" > df< / span > < span class = "o" > =< / span > < span class = "n" > pandas< / span > < span class = "o" > .< / span > < span class = "n" > DataFrame< / span > < span class = "p" > (< / span > < span class = "n" > decoded< / span > < span class = "p" > [< / span > < span class = "mi" > 0< / span > < span class = "p" > ],< / span > < span class = "n" > columns< / span > < span class = "o" > =< / span > < span class = "p" > [< / span > < span class = "s2" > " class_id" < / span > < span class = "p" > ,< / span > < span class = "s2" > " name" < / span > < span class = "p" > ,< / span > < span class = "s2" > " P" < / span > < span class = "p" > ])< / span >
2019-12-20 21:35:58 +00:00
< span class = "k" > print< / span > < span class = "p" > (< / span > < span class = "n" > df< / span > < span class = "p" > )< / span >
2019-10-30 16:35:16 +00:00
< / pre > < / div >
< / div >
< p class = "sphx-glr-script-out" > Out:< / p >
2019-12-20 21:35:58 +00:00
< div class = "sphx-glr-script-out highlight-none notranslate" > < div class = "highlight" > < pre > < span > < / span > class_id name P
0 n09468604 valley 0.785549
1 n09193705 alp 0.187054
2 n09399592 promontory 0.010602
3 n09246464 cliff 0.005537
4 n02417914 ibex 0.001997
2019-10-30 16:35:16 +00:00
< / pre > < / div >
< / div >
2019-12-20 21:35:58 +00:00
< p > < strong > Total running time of the script:< / strong > ( 0 minutes 56.895 seconds)< / p >
2019-10-30 16:35:16 +00:00
< div class = "sphx-glr-footer class sphx-glr-footer-example docutils container" id = "sphx-glr-download-auto-examples-plot-dl-keras-py" >
< div class = "sphx-glr-download docutils container" >
2019-12-20 21:35:58 +00:00
< a class = "reference download internal" href = "../_downloads/plot_dl_keras.py" download = "" > < 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_dl_keras.py< / span > < / code > < / a > < / div >
2019-10-30 16:35:16 +00:00
< div class = "sphx-glr-download docutils container" >
2019-12-20 21:35:58 +00:00
< a class = "reference download internal" href = "../_downloads/plot_dl_keras.ipynb" download = "" > < 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_dl_keras.ipynb< / span > < / code > < / a > < / div >
2019-10-30 16:35:16 +00:00
< / div >
< p class = "sphx-glr-signature" > < a class = "reference external" href = "https://sphinx-gallery.readthedocs.io" > Gallery generated by Sphinx-Gallery< / a > < / p >
< / div >
< / div >
2019-12-20 21:35:58 +00:00
< / div >
< / div >
< script src = "https://ajax.googleapis.com/ajax/libs/jquery/3.0.0/jquery.min.js"
integrity="sha384-THPy051/pYDQGanwU6poAc/hOdQxjnOEXzbT+OuUAFqNqFjL+4IGLBgCJC3ZOShY"
crossorigin="anonymous">< / script >
< script src = "https://cdnjs.cloudflare.com/ajax/libs/tether/1.2.0/js/tether.min.js"
integrity="sha384-Plbmg8JY28KFelvJVai01l8WyZzrYWG825m+cZ0eDDS1f7d/js6ikvy1+X+guPIB"
crossorigin="anonymous">< / script >
< script src = "https://maxcdn.bootstrapcdn.com/bootstrap/4.0.0-alpha.3/js/bootstrap.min.js"
integrity="sha384-ux8v3A6CPtOTqOzMKiuo3d/DomGaaClxFYdCu2HPMBEkf6x2xiDyJ7gkXU0MWwaD"
crossorigin="anonymous">< / script >
< script src = 'https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML' > < / script >
< script src = "https://cdnjs.cloudflare.com/ajax/libs/lunr.js/0.6.0/lunr.min.js" > < / script >
< script src = "../_static/searchtools.js" > < / script >
< script > $ ( '#searchbox' ) . show ( 0 ) < / script >
< / body >
2019-10-30 16:35:16 +00:00
< / html >
