This is an automated email from the ASF dual-hosted git repository. git-site-role pushed a commit to branch asf-site in repository https://gitbox.apache.org/repos/asf/beam.git
The following commit(s) were added to refs/heads/asf-site by this push: new 8bb4c428242 Publishing website 2023/04/18 22:17:00 at commit 1c63a02 8bb4c428242 is described below commit 8bb4c42824273e9e4740f8b5859ac59ef0b23b19 Author: jenkins <bui...@apache.org> AuthorDate: Tue Apr 18 22:17:01 2023 +0000 Publishing website 2023/04/18 22:17:00 at commit 1c63a02 --- website/generated-content/documentation/index.xml | 2 +- website/generated-content/documentation/ml/about-ml/index.html | 2 +- .../documentation/sdks/python-machine-learning/index.html | 2 +- website/generated-content/sitemap.xml | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/website/generated-content/documentation/index.xml b/website/generated-content/documentation/index.xml index 39a0289a1fe..5defb0ce992 100644 --- a/website/generated-content/documentation/index.xml +++ b/website/generated-content/documentation/index.xml @@ -106,7 +106,7 @@ that illustrates running Scikit-learn models with Apache Beam.</p> <li>Use tensorflow 2.7 or later.</li> <li>Pass the path of the model to the TensorFlow <code>ModelHandler</code> by using <code>model_uri=&lt;path_to_trained_model&gt;</code>.</li> <li>Alternatively, you can pass the path to saved weights of the trained model, a function to build the model using <code>create_model_fn=&lt;function&gt;</code>, and set the <code>model_type=ModelType.SAVED_WEIGHTS</code>. -See <a href="https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_tensorflow_with_tensorflowhub.ipynb">this notebook</a> that illustrates running Tensorflow models with Built-in model handlers.</li> +See <a href="https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_tensorflow.ipynb">this notebook</a> that illustrates running Tensorflow models with Built-in model handlers.</li> </ul> </li> <li>Using <code>tfx_bsl</code>. diff --git a/website/generated-content/documentation/ml/about-ml/index.html b/website/generated-content/documentation/ml/about-ml/index.html index 8e4e61e1f6a..e92768efd5a 100644 --- a/website/generated-content/documentation/ml/about-ml/index.html +++ b/website/generated-content/documentation/ml/about-ml/index.html @@ -29,7 +29,7 @@ that illustrates running PyTorch models with Apache Beam.</p><h4 id=scikit-learn <code>model_uri=<path_to_pickled_file></code> and <code>model_file_type: <ModelFileType></code>, where you can specify <code>ModelFileType.PICKLE</code> or <code>ModelFileType.JOBLIB</code>, depending on how the model was serialized.</li></ol><p>See <a href=https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_sklearn.ipynb>this notebook</a> that illustrates running Scikit-learn models with Apache Beam.</p><h4 id=tensorflow>TensorFlow</h4><p>To use TensorFlow with the RunInference API, you have two options:</p><ol><li>Use the built-in TensorFlow Model Handlers in Apache Beam SDK - <code>TFModelHandlerNumpy</code> and <code>TFModelHandlerTensor</code>.<ul><li>Depending on the type of input for your model, use <code>TFModelHandlerNumpy</code> for <code>numpy</code> input and <code>TFModelHandlerTensor</code> for <code>tf.Tenso [...] -See <a href=https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_tensorflow_with_tensorflowhub.ipynb>this notebook</a> that illustrates running Tensorflow models with Built-in model handlers.</li></ul></li><li>Using <code>tfx_bsl</code>.<ul><li>Use this approach if your model input is of type <code>tf.Example</code>.</li><li>Use <code>tfx_bsl</code> version 1.10.0 or later.</li><li>Create a model handler using <code>tfx_bsl.public.beam.run_inference.CreateM [...] +See <a href=https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_tensorflow.ipynb>this notebook</a> that illustrates running Tensorflow models with Built-in model handlers.</li></ul></li><li>Using <code>tfx_bsl</code>.<ul><li>Use this approach if your model input is of type <code>tf.Example</code>.</li><li>Use <code>tfx_bsl</code> version 1.10.0 or later.</li><li>Create a model handler using <code>tfx_bsl.public.beam.run_inference.CreateModelHandler()</code [...] See <a href=https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_tensorflow.ipynb>this notebook</a> that illustrates running TensorFlow models with Apache Beam and tfx-bsl.</li></ul></li></ol><h2 id=automatic-model-refresh>Automatic model refresh</h2><p>To automatically update the model being used with the RunInference <code>PTransform</code> without stopping the pipeline, pass a <a href=https://beam.apache.org/releases/pydoc/current/apache_beam.ml.inference.base.html#apache_beam.ml.inference.base.ModelMetadata><code>ModelMetadata</code></a> side input <code>PCollection</code> to the R [...] an update to the side input. This could happen with global windowed side inputs with data driven triggers, such as <code>AfterCount</code> and <code>AfterProcessingTime</code>. Until the side input is updated, emit the default or initial model ID that is used to pass the respective <code>ModelHandler</code> as a side input.</p><h2 id=custom-inference>Custom Inference</h2><p>The RunInference API doesn’t currently support making remote inference calls using, for example, the Natural [...] diff --git a/website/generated-content/documentation/sdks/python-machine-learning/index.html b/website/generated-content/documentation/sdks/python-machine-learning/index.html index 04aa8a31a89..8b7811f281a 100644 --- a/website/generated-content/documentation/sdks/python-machine-learning/index.html +++ b/website/generated-content/documentation/sdks/python-machine-learning/index.html @@ -39,7 +39,7 @@ that illustrates running PyTorch models with Apache Beam.</p><h3 id=scikit-learn <code>model_uri=<path_to_pickled_file></code> and <code>model_file_type: <ModelFileType></code>, where you can specify <code>ModelFileType.PICKLE</code> or <code>ModelFileType.JOBLIB</code>, depending on how the model was serialized.</li></ol><p>See <a href=https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_sklearn.ipynb>this notebook</a> that illustrates running Scikit-learn models with Apache Beam.</p><h3 id=tensorflow>TensorFlow</h3><p>To use TensorFlow with the RunInference API, you have two options:</p><ol><li>Use the built-in TensorFlow Model Handlers in Apache Beam SDK - <code>TFModelHandlerNumpy</code> and <code>TFModelHandlerTensor</code>.<ul><li>Depending on the type of input for your model, use <code>TFModelHandlerNumpy</code> for <code>numpy</code> input and <code>TFModelHandlerTensor</code> for <code>tf.Tenso [...] -See <a href=https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_tensorflow_with_tensorflowhub.ipynb>this notebook</a> that illustrates running Tensorflow models with Built-in model handlers.</li></ul></li><li>Using <code>tfx_bsl</code>.<ul><li>Use this approach if your model input is of type <code>tf.Example</code>.</li><li>Use <code>tfx_bsl</code> version 1.10.0 or later.</li><li>Create a model handler using <code>tfx_bsl.public.beam.run_inference.CreateM [...] +See <a href=https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_tensorflow.ipynb>this notebook</a> that illustrates running Tensorflow models with Built-in model handlers.</li></ul></li><li>Using <code>tfx_bsl</code>.<ul><li>Use this approach if your model input is of type <code>tf.Example</code>.</li><li>Use <code>tfx_bsl</code> version 1.10.0 or later.</li><li>Create a model handler using <code>tfx_bsl.public.beam.run_inference.CreateModelHandler()</code [...] See <a href=https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_tensorflow.ipynb>this notebook</a> that illustrates running TensorFlow models with Apache Beam and tfx-bsl.</li></ul></li></ol><h2 id=use-custom-models>Use custom models</h2><p>If you would like to use a model that isn’t specified by one of the supported frameworks, the RunInference API is designed flexibly to allow you to use any custom machine learning models. You only need to create your own <code>ModelHandler</code> or <code>KeyedModelHandler</code> with logic to load your model and use it to run the inference.</p><p>A simple example can be found in <a href=https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_custom_inference.ipynb>this notebook</a>. diff --git a/website/generated-content/sitemap.xml b/website/generated-content/sitemap.xml index 9103d943b91..a4979c10191 100644 --- a/website/generated-content/sitemap.xml +++ b/website/generated-content/sitemap.xml @@ -1 +1 @@ -<?xml version="1.0" encoding="utf-8" standalone="yes"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:xhtml="http://www.w3.org/1999/xhtml"><url><loc>/blog/beam-2.46.0/</loc><lastmod>2023-04-18T11:41:46-04:00</lastmod></url><url><loc>/categories/blog/</loc><lastmod>2023-04-18T11:41:46-04:00</lastmod></url><url><loc>/blog/</loc><lastmod>2023-04-18T11:41:46-04:00</lastmod></url><url><loc>/categories/</loc><lastmod>2023-04-18T11:41:46-04:00</lastmod></url><url><loc>/catego [...] \ No newline at end of file +<?xml version="1.0" encoding="utf-8" standalone="yes"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:xhtml="http://www.w3.org/1999/xhtml"><url><loc>/blog/beam-2.46.0/</loc><lastmod>2023-04-18T16:44:37-04:00</lastmod></url><url><loc>/categories/blog/</loc><lastmod>2023-04-18T16:44:37-04:00</lastmod></url><url><loc>/blog/</loc><lastmod>2023-04-18T16:44:37-04:00</lastmod></url><url><loc>/categories/</loc><lastmod>2023-04-18T16:44:37-04:00</lastmod></url><url><loc>/catego [...] \ No newline at end of file