Execute a sub graph on a remote processor.
The graph specifications(such as graph itself, input tensors and output names) are stored as a serialized protocol buffer of RemoteFusedGraphExecuteInfo as serialized_remote_fused_graph_execute_info. The specifications will be passed to a dedicated registered remote fused graph executor. The executor will send the graph specifications to a remote processor and execute that graph. The execution results will be passed to consumer nodes as outputs of this node.
Constants
String | OP_NAME | The name of this op, as known by TensorFlow core engine |
Public Methods
static RemoteFusedGraphExecute | |
Iterator<Operand<TType>> |
iterator()
|
List<Output<?>> |
outputs()
Arbitrary number of tensors with arbitrary data types
|
Inherited Methods
Constants
public static final String OP_NAME
The name of this op, as known by TensorFlow core engine
Public Methods
public static RemoteFusedGraphExecute create (Scope scope, Iterable<Operand<?>> inputs, List<Class<? extends TType>> Toutputs, String serializedRemoteFusedGraphExecuteInfo)
Factory method to create a class wrapping a new RemoteFusedGraphExecute operation.
Parameters
scope | current scope |
---|---|
inputs | Arbitrary number of tensors with arbitrary data types |
serializedRemoteFusedGraphExecuteInfo | Serialized protocol buffer of RemoteFusedGraphExecuteInfo which contains graph specifications. |
Returns
- a new instance of RemoteFusedGraphExecute