Python ML tutorials

Learn how to train machine learning models for classification and prediction by following the steps in interactive notebooks. These tutorials integrate Dataflow into end-to-end machine learning workflows. You can also view the tutorials in GitHub.


Land cover image segmentation

This land classification model uses a TensorFlow framework and satellite data from Google Earth Engine to demonstrate semantic segmentation. The tutorial uses TensorFlow in Vertex AI to train the model, TensorFlow in Cloud Run to make real-time predictions, and Dataflow to make batch predictions. View the code on GitHub.

Open In Colab


Weather forecasting time series regression

This weather forecasting model uses a PyTorch framework and satellite data from Google Earth Engine to forecast precipitation for the next two and six hours. The tutorial uses PyTorch to create a fully convolutional network, Vertex AI to train the model, Dataflow to create the dataset, and PyTorch to make local predictions. View the code on GitHub.

Open In Colab


Global fishing watch time series classification

This classification model uses a TensorFlow framework and Maritime Mobile Service Identity (MMSI) location data to classify whether a ship is fishing every hour. The tutorial uses Keras and TensorFlow to train the model, Dataflow to create the dataset, and Keras in Cloud Run to make local predictions. View the code on GitHub.

Open In Colab


Wildlife image classification

This classification model uses an AutoML framework to create a model trained to recognize animal species from camera trap pictures. The tutorial uses AutoML in Vertex AI to train the model, Dataflow to create the dataset, and Vertex AI to make predictions. View the code on GitHub.

Open In Colab