Google Git
Sign in
apache / beam / refs/heads/onboard_python_tests / . / examples / notebooks / beam-ml
tree: 52a5b0e1960a8522ffae189e0b7261f4b4fd261c [path history] [tgz]
  1. automatic_model_refresh.ipynb
  2. custom_remote_inference.ipynb
  3. dataframe_api_preprocessing.ipynb
  4. image_processing_tensorflow.ipynb
  5. mltransform_basic.ipynb
  6. nlp_tensorflow_streaming.ipynb
  7. README.md
  8. run_custom_inference.ipynb
  9. run_inference_generative_ai.ipynb
  10. run_inference_huggingface.ipynb
  11. run_inference_multi_model.ipynb
  12. run_inference_pytorch.ipynb
  13. run_inference_pytorch_tensorflow_sklearn.ipynb
  14. run_inference_sklearn.ipynb
  15. run_inference_tensorflow.ipynb
  16. run_inference_tensorflow_with_tfx.ipynb
  17. run_inference_vertex_ai.ipynb
  18. run_inference_windowing.ipynb
  19. run_inference_with_tensorflow_hub.ipynb
  20. run_inference_xgboost.ipynb
  21. speech_emotion_tensorflow.ipynb
  22. tfma_beam.ipynb
examples/notebooks/beam-ml/README.md

ML Sample Notebooks

Starting with the Apache Beam SDK version 2.40, users have access to a RunInference transform.

This transform allows you to make predictions and inference on data with machine learning (ML) models. The model handler abstracts the user from the configuration needed for specific frameworks, such as Tensorflow, PyTorch, and others. For a full list of supported frameworks, see the Apache Beam Machine Learning page.

Using The Notebooks

These notebooks illustrate ways to use Apache Beam's RunInference transforms, as well as different use cases for ModelHandler implementations. Beam comes with multiple ModelHandler implementations.

Loading the Notebooks

  1. To get started quickly with notebooks, use Colab.
  2. In Colab, open the notebook from GitHub using the notebook URL, for example:
https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_tensorflow.ipynb
  1. To run most notebooks, you need to change the Google Cloud project and bucket to your project and bucket.

Notebooks

This section contains the following example notebooks.

Prediction and inference with pretrained models

Custom inference

Machine Learning Use Cases

Automatic Model Refresh

Multi-model pipelines

Model Evaluation

Data processing