Uses of Package
org.tribuo.interop.tensorflow
Package
Description
Provides an interface to TensorFlow, allowing the training of non-sequential models using any supported
Tribuo output type.
Provides an interface for working with TensorFlow sequence models, using Tribuo's
SequenceModel
abstraction.-
ClassDescriptionConverts a sparse example into a dense float vector, then wraps it in a
TFloat32
.An enum for the gradient optimisers exposed by TensorFlow-Java.Image converter.Can convert aLabel
into aTensor
containing one hot encoding of the label and can convert aTFloat16
orTFloat32
into aPrediction
or aLabel
.Can convert aMultiLabel
into aTensor
containing a binary encoding of the label vector and can convert aTFloat16
orTFloat32
into aPrediction
or aMultiLabel
.Converts theOutput
into aTensor
and vice versa.This model encapsulates a simple model with an input feed dict, and produces a single output tensor.A Tribuo wrapper around a TensorFlow frozen model.Base class for a TensorFlow model that operates onExample
s.This model encapsulates a TensorFlow model running in graph mode with a single tensor output.A Tribuo wrapper around a TensorFlow saved model bundle.The model format to emit.A serializable tuple containing the tensor class name, the shape and the data.A map of names and tensors to feed into a session.Type of feature extractor. -