These examples include using pre-trained models for image classification and object detection, and driving the training of a pre-defined model - all using the TensorFlow Java API.

The TensorFlow Java API does not have feature parity with the Python API. The Java API is most suitable for inference using pre-trained models and for training pre-defined models from a single Java process.

Python will be the most convenient language for defining the numerical computation of a model.

• Slides from January 2018.
• See README.md in each subdirectory for details.