Package org.tribuo.interop.tensorflow

Provides an interface to Tensorflow, allowing the training of non-sequential models using any supported Tribuo output type.

See: Description

Interface Summary

Interface	Description
ExampleTransformer<T extends Output<T>>	TensorFlow support is experimental, and may change without a major version bump.
OutputTransformer<T extends Output<T>>	TensorFlow support is experimental, and may change without a major version bump.

Class Summary

Class	Description
DenseTransformer<T extends Output<T>>	Converts a sparse example into a dense float vector, then wraps it in a Tensor.
ImageTransformer<T extends Output<T>>	Image transformer.
LabelTransformer	Can convert a Label into a Tensor containing a 32-bit integer and can convert a vector of 32-bit floats into a Prediction or a Label.
RegressorTransformer	Can convert a Regressor to a Tensor containing a 32-bit float and a Tensor into a Prediction or Regressor.
TensorflowCheckpointModel<T extends Output<T>>	TensorFlow support is experimental, and may change without a major version bump.
TensorflowCheckpointTrainer<T extends Output<T>>	Trainer for Tensorflow.
TensorflowCheckpointTrainer.TensorflowCheckpointTrainerProvenance
TensorflowExternalModel<T extends Output<T>>	A Tribuo wrapper around a Tensorflow frozen model.
TensorflowModel<T extends Output<T>>	This model encapsulates a simple model with a single input tensor (labelled TensorflowModel.INPUT_NAME), and produces a single output tensor (labelled TensorflowModel.OUTPUT_NAME).
TensorflowTrainer<T extends Output<T>>	Trainer for Tensorflow.
TensorflowTrainer.TensorflowTrainerProvenance
TensorflowUtil	Helper functions for working with Tensorflow.
TrainTest	Build and run a Tensorflow multi-class classifier for a standard dataset.
TrainTest.TensorflowOptions

Enum Summary

Enum	Description
TrainTest.InputType

Package org.tribuo.interop.tensorflow Description

Provides an interface to Tensorflow, allowing the training of non-sequential models using any supported Tribuo output type.

There are two main interfaces for interacting with Tensorflow Tensors, ExampleTransformer and OutputTransformer, with provide conversions to and from Tribuo's features and outputs respectively. There are implementations of a dense feature transformation and one for images as 3d arrays, along with output transformers for Label and Regressor.

N.B. Tensorflow support is experimental and may change without a major version bump.