To get started, see the installation instructions.
- 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.
Additional examples can be found in the tensorflow/java GitHub repository.
|ExecutionEnvironment||Defines an environment for creating and executing TensorFlow
|Graph.WhileSubgraphBuilder||Used to instantiate an abstract class which overrides the buildSubgraph method to build a conditional or body subgraph for a while loop.|
|Operand<T>||Interface implemented by operands of a TensorFlow operation.|
|Operation||Performs computation on Tensors.|
|OperationBuilder||A builder for
|EagerSession||An environment for executing TensorFlow operations eagerly.|
|Graph||A data flow graph representing a TensorFlow computation.|
|GraphOperation||Implementation for an
|Output<T>||A symbolic handle to a tensor produced by an
|SavedModelBundle||SavedModelBundle represents a model loaded from storage.|
|SavedModelBundle.Loader||Options for loading a SavedModel.|
|Server||An in-process TensorFlow server, for use in distributed training.|
|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<T>||A statically typed multi-dimensional array whose elements are of a type described by T.|
|TensorFlow||Static utility methods describing the TensorFlow runtime.|
|Tensors||Type-safe factory methods for creating
|DataType||Represents the type of elements in a
|EagerSession.DevicePlacementPolicy||Controls how to act when we try to run an operation on a given device but some input tensors are not on that device.|
|EagerSession.ResourceCleanupStrategy||Controls how TensorFlow resources are cleaned up when they are no longer needed.|
|TensorFlowException||Unchecked exception thrown when executing TensorFlow Graphs.|