org.bytedeco.javacpp

Class tensorflow.Session

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.javacpp.helper.tensorflow.AbstractSession

org.bytedeco.javacpp.tensorflow.Session

All Implemented Interfaces:

AutoCloseable

Direct Known Subclasses:

tensorflow.AbstractSession.DeleteDeallocator

Enclosing class:

tensorflow

@Namespace(value="tensorflow")
public static class tensorflow.Session
extends tensorflow.AbstractSession

\brief A Session instance lets a caller drive a TensorFlow graph computation. When a Session is created with a given target, a new Session object is bound to the universe of resources specified by that target. Those resources are available to this session to perform computation described in the GraphDef. After extending the session with a graph, the caller uses the Run() API to perform the computation and potentially fetch outputs as Tensors. Example:

 c++
 
      tensorflow::GraphDef graph;
      // ... Create or load graph into "graph".
 
      // This example uses the default options which connects
      // to a local runtime.
      tensorflow::SessionOptions options;
      std::unique_ptr<tensorflow::Session>
      session(tensorflow::NewSession(options));
 
      // Create the session with this graph.
      tensorflow::Status s = session->Create(graph);
      if (!s.ok()) { ... }
 
      // Run the graph and fetch the first output of the "output"
      // operation, and also run to but do not return anything
      // for the "update_state" operation.
      std::vector<tensorflow::Tensor> outputs;
      s = session->Run({}, {"output:0"}, {"update_state"}, &outputs);
      if (!s.ok()) { ... }
 
      // Map the output as a flattened float tensor, and do something
      // with it.
      auto output_tensor = outputs[0].flat<float>();
      if (output_tensor(0) > 0.5) { ... }
 
      // Close the session to release the resources associated with
      // this session.
      session->Close();
 
  

A Session allows concurrent calls to Run(), though a Session must be created / extended by a single thread. Only one thread must call Close(), and Close() must only be called after all other calls to Run() have returned.

Nested Class Summary

Nested classes/interfaces inherited from class org.bytedeco.javacpp.helper.tensorflow.AbstractSession

tensorflow.AbstractSession.DeleteDeallocator

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator

Field Summary

Fields inherited from class org.bytedeco.javacpp.Pointer

address, capacity, limit, position

Constructor Summary

Constructors

Constructor and Description
Session(Pointer p) Pointer cast constructor.
Session(tensorflow.SessionOptions options) Calls tensorflow.NewSession(SessionOptions) and registers a deallocator.

Method Summary

Modifier and Type	Method and Description
tensorflow.Status	Close() \brief Closes this session.
tensorflow.Status	Close(tensorflow.RunOptions run_options)
tensorflow.Status	Create(tensorflow.GraphDef graph) \brief Create the graph to be used for the session.
tensorflow.Status	Create(tensorflow.RunOptions run_options, tensorflow.GraphDef graph) NOTE: This API is still experimental and may change.
tensorflow.Status	Extend(tensorflow.GraphDef graph) \brief Adds operations to the graph that is already registered with the Session.
tensorflow.Status	Extend(tensorflow.RunOptions run_options, tensorflow.GraphDef graph)
tensorflow.Status	ListDevices(tensorflow.DeviceAttributes response) \brief List devices in the session.
tensorflow.Status	LocalDeviceManager(PointerPointer output)
tensorflow.Status	LocalDeviceManager(tensorflow.DeviceMgr output)
tensorflow.Status	MakeCallable(tensorflow.CallableOptions callable_options, long... out_handle)
tensorflow.Status	MakeCallable(tensorflow.CallableOptions callable_options, LongBuffer out_handle)
tensorflow.Status	MakeCallable(tensorflow.CallableOptions callable_options, LongPointer out_handle) \brief Creates a handle for invoking the subgraph defined by callable_options.
tensorflow.Status	PRun(BytePointer handle, tensorflow.StringTensorPairVector inputs, tensorflow.StringVector output_names, tensorflow.TensorVector outputs) \brief Continues the pending execution specified by handle with the provided input tensors and fills outputs for the endpoints specified in output_names.
tensorflow.Status	PRun(String handle, tensorflow.StringTensorPairVector inputs, tensorflow.StringVector output_names, tensorflow.TensorVector outputs)
tensorflow.Status	PRunSetup(tensorflow.StringVector input_names, tensorflow.StringVector output_names, tensorflow.StringVector target_nodes, BytePointer handle) \brief Sets up a graph for partial execution.
tensorflow.Status	ReleaseCallable(long handle) \brief Releases resources associated with the given handle in this session.
tensorflow.Status	Run(tensorflow.RunOptions run_options, tensorflow.StringTensorPairVector inputs, tensorflow.StringVector output_tensor_names, tensorflow.StringVector target_node_names, tensorflow.TensorVector outputs, tensorflow.RunMetadata run_metadata) \brief Like Run, but allows users to pass in a RunOptions proto and to retrieve non-Tensor metadata output via a RunMetadata proto for this step.
tensorflow.Status	Run(tensorflow.StringTensorPairVector inputs, tensorflow.StringVector output_tensor_names, tensorflow.StringVector target_node_names, tensorflow.TensorVector outputs) \brief Runs the graph with the provided input tensors and fills outputs for the endpoints specified in output_tensor_names.
tensorflow.Status	RunCallable(long handle, tensorflow.TensorVector feed_tensors, tensorflow.TensorVector fetch_tensors, tensorflow.RunMetadata run_metadata) \brief Invokes the subgraph named by handle with the given options and input tensors.

Methods inherited from class org.bytedeco.javacpp.helper.tensorflow.AbstractSession

delete

Methods inherited from class org.bytedeco.javacpp.Pointer

address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, hashCode, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetof, parseBytes, physicalBytes, position, position, put, realloc, setNull, sizeof, toString, totalBytes, totalPhysicalBytes, withDeallocator, zero

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

Session

public Session(Pointer p)

Pointer cast constructor. Invokes Pointer.Pointer(Pointer).

Session

public Session(tensorflow.SessionOptions options)

Calls tensorflow.NewSession(SessionOptions) and registers a deallocator.

Method Detail

Create

@ByVal
public tensorflow.Status Create(@Const @ByRef
                                        tensorflow.GraphDef graph)

\brief Create the graph to be used for the session. Returns an error if this session has already been created with a graph. To re-use the session with a different graph, the caller must Close() the session first.

Extend

@ByVal
public tensorflow.Status Extend(@Const @ByRef
                                        tensorflow.GraphDef graph)

\brief Adds operations to the graph that is already registered with the Session. The names of new operations in "graph" must not exist in the graph that is already registered.

Run

@ByVal
public tensorflow.Status Run(@Const @ByRef
                                     tensorflow.StringTensorPairVector inputs,
                                     @Const @ByRef
                                     tensorflow.StringVector output_tensor_names,
                                     @Const @ByRef
                                     tensorflow.StringVector target_node_names,
                                     tensorflow.TensorVector outputs)

\brief Runs the graph with the provided input tensors and fills outputs for the endpoints specified in output_tensor_names. Runs to but does not return Tensors for the nodes in target_node_names. The order of tensors in outputs will match the order provided by output_tensor_names. If Run returns OK(), then outputs->size() will be equal to output_tensor_names.size(). If Run does not return OK(), the state of outputs is undefined. REQUIRES: The name of each Tensor of the input or output must match a "Tensor endpoint" in the GraphDef passed to Create(). REQUIRES: At least one of output_tensor_names and target_node_names must be non-empty. REQUIRES: outputs is not nullptr if output_tensor_names is non-empty.

Create

@ByVal
public tensorflow.Status Create(@Const @ByRef
                                        tensorflow.RunOptions run_options,
                                        @Const @ByRef
                                        tensorflow.GraphDef graph)

NOTE: This API is still experimental and may change.

Extend

@ByVal
public tensorflow.Status Extend(@Const @ByRef
                                        tensorflow.RunOptions run_options,
                                        @Const @ByRef
                                        tensorflow.GraphDef graph)

Close

@ByVal
public tensorflow.Status Close(@Const @ByRef
                                       tensorflow.RunOptions run_options)

Run

@ByVal
public tensorflow.Status Run(@Const @ByRef
                                     tensorflow.RunOptions run_options,
                                     @Const @ByRef
                                     tensorflow.StringTensorPairVector inputs,
                                     @Const @ByRef
                                     tensorflow.StringVector output_tensor_names,
                                     @Const @ByRef
                                     tensorflow.StringVector target_node_names,
                                     tensorflow.TensorVector outputs,
                                     tensorflow.RunMetadata run_metadata)

\brief Like Run, but allows users to pass in a RunOptions proto and to retrieve non-Tensor metadata output via a RunMetadata proto for this step. run_metadata may be nullptr, in which case any metadata output is discarded. NOTE: This API is still experimental and may change.

PRunSetup

@ByVal
public tensorflow.Status PRunSetup(@Const @ByRef
                                           tensorflow.StringVector input_names,
                                           @Const @ByRef
                                           tensorflow.StringVector output_names,
                                           @Const @ByRef
                                           tensorflow.StringVector target_nodes,
                                           @StdString @Cast(value={"char*","std::string*"})
                                           BytePointer handle)

\brief Sets up a graph for partial execution. All future feeds and fetches are specified by input_names and output_names. Returns handle that can be used to perform a sequence of partial feeds and fetches. NOTE: This API is still experimental and may change.

PRun

@ByVal
public tensorflow.Status PRun(@StdString
                                      BytePointer handle,
                                      @Const @ByRef
                                      tensorflow.StringTensorPairVector inputs,
                                      @Const @ByRef
                                      tensorflow.StringVector output_names,
                                      tensorflow.TensorVector outputs)

\brief Continues the pending execution specified by handle with the provided input tensors and fills outputs for the endpoints specified in output_names. NOTE: This API is still experimental and may change.

PRun

@ByVal
public tensorflow.Status PRun(@StdString
                                      String handle,
                                      @Const @ByRef
                                      tensorflow.StringTensorPairVector inputs,
                                      @Const @ByRef
                                      tensorflow.StringVector output_names,
                                      tensorflow.TensorVector outputs)

ListDevices

@ByVal
public tensorflow.Status ListDevices(@StdVector
                                             tensorflow.DeviceAttributes response)

\brief List devices in the session. Retrieves the list of available devices within the session, and populates *response. This API is optional. If it is unimplemented, Status will return a corresponding error message, and *response will be unmodified.

Close

@ByVal
public tensorflow.Status Close()

\brief Closes this session. Closing a session releases the resources used by this session on the TensorFlow runtime (specified during session creation by the SessionOptions::target field).

LocalDeviceManager

@ByVal
public tensorflow.Status LocalDeviceManager(@Cast(value="const tensorflow::DeviceMgr**")
                                                    PointerPointer output)

LocalDeviceManager

@ByVal
public tensorflow.Status LocalDeviceManager(@Const @ByPtrPtr
                                                    tensorflow.DeviceMgr output)

MakeCallable

@ByVal
public tensorflow.Status MakeCallable(@Const @ByRef
                                              tensorflow.CallableOptions callable_options,
                                              @Cast(value="tensorflow::Session::CallableHandle*")
                                              LongPointer out_handle)

\brief Creates a handle for invoking the subgraph defined by callable_options. NOTE: This API is still experimental and may change.

MakeCallable

@ByVal
public tensorflow.Status MakeCallable(@Const @ByRef
                                              tensorflow.CallableOptions callable_options,
                                              @Cast(value="tensorflow::Session::CallableHandle*")
                                              LongBuffer out_handle)

MakeCallable

@ByVal
public tensorflow.Status MakeCallable(@Const @ByRef
                                              tensorflow.CallableOptions callable_options,
                                              @Cast(value="tensorflow::Session::CallableHandle*")
                                              long... out_handle)

RunCallable

@ByVal
public tensorflow.Status RunCallable(@Cast(value="tensorflow::Session::CallableHandle")
                                             long handle,
                                             @Const @ByRef
                                             tensorflow.TensorVector feed_tensors,
                                             tensorflow.TensorVector fetch_tensors,
                                             tensorflow.RunMetadata run_metadata)

\brief Invokes the subgraph named by handle with the given options and input tensors. The order of tensors in feed_tensors must and fetch_tensors will match the order of names in CallableOptions::feed() and CallableOptions::fetch() when this subgraph was created. NOTE: This API is still experimental and may change.

ReleaseCallable

@ByVal
public tensorflow.Status ReleaseCallable(@Cast(value="tensorflow::Session::CallableHandle")
                                                 long handle)

\brief Releases resources associated with the given handle in this session. NOTE: This API is still experimental and may change.