Package org.tribuo.interop.tensorflow
package org.tribuo.interop.tensorflow
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.
-
ClassDescriptionDenseTransformer<T extends Output<T>>Converts a sparse example into a dense float vector, then wraps it in a
Tensor.ExampleTransformer<T extends Output<T>>TensorFlow support is experimental, and may change without a major version bump.ImageTransformer<T extends Output<T>>Image transformer.Can convert aLabelinto aTensorcontaining a 32-bit integer and can convert a vector of 32-bit floats into aPredictionor aLabel.OutputTransformer<T extends Output<T>>TensorFlow support is experimental, and may change without a major version bump.Can convert aRegressorto aTensorcontaining a 32-bit float and a Tensor into aPredictionor 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.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 (labelledTensorflowModel.INPUT_NAME), and produces a single output tensor (labelledTensorflowModel.OUTPUT_NAME).TensorflowTrainer<T extends Output<T>>Trainer for Tensorflow.Helper functions for working with Tensorflow.Build and run a Tensorflow multi-class classifier for a standard dataset.