Package org.tensorflow

Defines classes to build, save, load and execute TensorFlow models.

See: Description

Class Summary

Class	Description
Graph	A data flow graph representing a TensorFlow computation.
Operation	A Graph node that performs computation on Tensors.
OperationBuilder	A builder for Operations in a Graph.
Output	A symbolic handle to a tensor produced by an Operation.
SavedModelBundle	SavedModelBundle represents a model loaded from storage.
Session	Driver for Graph execution.
Session.Run	Output tensors and metadata obtained when executing a session.
Shape	The possibly partially known shape of a tensor produced by an operation.
Tensor	A typed multi-dimensional array.
TensorFlow	Static utility methods describing the TensorFlow runtime.

Enum Summary

Enum	Description
DataType	Type of elements in a Tensor.

Exception Summary

Exception	Description
TensorFlowException	Unchecked exception thrown when executing TensorFlow Graphs.

Package org.tensorflow Description

Defines classes to build, save, load and execute TensorFlow models.

WARNING: The API is currently experimental and is not covered by TensorFlow API stability guarantees. See README.md for installation instructions.

The LabelImage example demonstrates use of this API to classify images using a pre-trained Inception architecture convolutional neural network. It demonstrates:

• Graph construction: using the OperationBuilder class to construct a graph to decode, resize and normalize a JPEG image.
• Model loading: Using Graph.importGraphDef() to load a pre-trained Inception model.
• Graph execution: Using a Session to execute the graphs and find the best label for an image.