RPCOptionsOrBuilder
Mantieni tutto organizzato con le raccolte
Salva e classifica i contenuti in base alle tue preferenze.
| Sottoclassi indirette conosciute |
Metodi pubblici
| booleano astratto | getCacheRpcResponse ()
Setting cache_rpc_response to true will enable sender side caching of
response for RecvTensorAsync and RecvBufAsync to allow receiver to retry
requests . |
| stringa astratta | |
| astratto com.google.protobuf.ByteString | |
| astratto int | |
| booleano astratto | |
| booleano astratto | |
Metodi pubblici
pubblico astratto booleano getCacheRpcResponse ()
Setting cache_rpc_response to true will enable sender side caching of
response for RecvTensorAsync and RecvBufAsync to allow receiver to retry
requests . This is only necessary when the network fabric is experiencing a
significant error rate. Without it we'll fail a step on an network error,
while with it we'll be able to complete long steps (like complex
initializations) in the face of some network errors during RecvTensor.
bool cache_rpc_response = 4; public abstract String getCompressionAlgorithm ()
The compression algorithm to be used. One of "deflate", "gzip".
string compression_algorithm = 2; public abstract com.google.protobuf.ByteString getCompressionAlgorithmBytes ()
The compression algorithm to be used. One of "deflate", "gzip".
string compression_algorithm = 2; public abstract int getCompressionLevel ()
If compression_algorithm is set, the compression level to be used.
From 0 (no compression), up to 3.
int32 compression_level = 3; pubblico astratto booleano getDisableSessionConnectionSharing ()
Disables TCP connection sharing when opening a new RPC channel.
bool disable_session_connection_sharing = 5; pubblico astratto booleano getUseRpcForInprocessMaster ()
If true, always use RPC to contact the session target.
If false (the default option), TensorFlow may use an optimized
transport for client-master communication that avoids the RPC
stack. This option is primarily for used testing the RPC stack.
bool use_rpc_for_inprocess_master = 1;
Salvo quando diversamente specificato, i contenuti di questa pagina sono concessi in base alla licenza Creative Commons Attribution 4.0, mentre gli esempi di codice sono concessi in base alla licenza Apache 2.0. Per ulteriori dettagli, consulta le norme del sito di Google Developers. Java è un marchio registrato di Oracle e/o delle sue consociate.
Ultimo aggiornamento 2025-07-27 UTC.
[null,null,["Ultimo aggiornamento 2025-07-27 UTC."],[],[],null,["# RPCOptionsOrBuilder\n\npublic interface **RPCOptionsOrBuilder** \n\n|---|---|---|\n| Known Indirect Subclasses [RPCOptions](/jvm/api_docs/java/org/tensorflow/proto/framework/RPCOptions), [RPCOptions.Builder](/jvm/api_docs/java/org/tensorflow/proto/framework/RPCOptions.Builder) |--------------------------------------------------------------------------------------------|---------------------------------------| | [RPCOptions](/jvm/api_docs/java/org/tensorflow/proto/framework/RPCOptions) | Protobuf type `tensorflow.RPCOptions` | | [RPCOptions.Builder](/jvm/api_docs/java/org/tensorflow/proto/framework/RPCOptions.Builder) | Protobuf type `tensorflow.RPCOptions` | |||\n\n### Public Methods\n\n|-----------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| abstract boolean | [getCacheRpcResponse](/jvm/api_docs/java/org/tensorflow/proto/framework/RPCOptionsOrBuilder#getCacheRpcResponse())() ``` Setting cache_rpc_response to true will enable sender side caching of response for RecvTensorAsync and RecvBufAsync to allow receiver to retry requests . ``` |\n| abstract String | [getCompressionAlgorithm](/jvm/api_docs/java/org/tensorflow/proto/framework/RPCOptionsOrBuilder#getCompressionAlgorithm())() ``` The compression algorithm to be used. ``` |\n| abstract com.google.protobuf.ByteString | [getCompressionAlgorithmBytes](/jvm/api_docs/java/org/tensorflow/proto/framework/RPCOptionsOrBuilder#getCompressionAlgorithmBytes())() ``` The compression algorithm to be used. ``` |\n| abstract int | [getCompressionLevel](/jvm/api_docs/java/org/tensorflow/proto/framework/RPCOptionsOrBuilder#getCompressionLevel())() ``` If compression_algorithm is set, the compression level to be used. ``` |\n| abstract boolean | [getDisableSessionConnectionSharing](/jvm/api_docs/java/org/tensorflow/proto/framework/RPCOptionsOrBuilder#getDisableSessionConnectionSharing())() ``` Disables TCP connection sharing when opening a new RPC channel. ``` |\n| abstract boolean | [getUseRpcForInprocessMaster](/jvm/api_docs/java/org/tensorflow/proto/framework/RPCOptionsOrBuilder#getUseRpcForInprocessMaster())() ``` If true, always use RPC to contact the session target. ``` |\n\nPublic Methods\n--------------\n\n#### public abstract boolean\n**getCacheRpcResponse**\n()\n\n\u003cbr /\u003e\n\n```\n Setting cache_rpc_response to true will enable sender side caching of\n response for RecvTensorAsync and RecvBufAsync to allow receiver to retry\n requests . This is only necessary when the network fabric is experiencing a\n significant error rate. Without it we'll fail a step on an network error,\n while with it we'll be able to complete long steps (like complex\n initializations) in the face of some network errors during RecvTensor.\n \n```\n`bool cache_rpc_response = 4;`\n\n\u003cbr /\u003e\n\n#### public abstract String\n**getCompressionAlgorithm**\n()\n\n\u003cbr /\u003e\n\n```\n The compression algorithm to be used. One of \"deflate\", \"gzip\".\n \n```\n`string compression_algorithm = 2;`\n\n\u003cbr /\u003e\n\n#### public abstract com.google.protobuf.ByteString\n**getCompressionAlgorithmBytes**\n()\n\n\u003cbr /\u003e\n\n```\n The compression algorithm to be used. One of \"deflate\", \"gzip\".\n \n```\n`string compression_algorithm = 2;`\n\n\u003cbr /\u003e\n\n#### public abstract int\n**getCompressionLevel**\n()\n\n\u003cbr /\u003e\n\n```\n If compression_algorithm is set, the compression level to be used.\n From 0 (no compression), up to 3.\n \n```\n`int32 compression_level = 3;`\n\n\u003cbr /\u003e\n\n#### public abstract boolean\n**getDisableSessionConnectionSharing**\n()\n\n\u003cbr /\u003e\n\n```\n Disables TCP connection sharing when opening a new RPC channel.\n \n```\n`bool disable_session_connection_sharing = 5;`\n\n\u003cbr /\u003e\n\n#### public abstract boolean\n**getUseRpcForInprocessMaster**\n()\n\n\u003cbr /\u003e\n\n```\n If true, always use RPC to contact the session target.\n If false (the default option), TensorFlow may use an optimized\n transport for client-master communication that avoids the RPC\n stack. This option is primarily for used testing the RPC stack.\n \n```\n`bool use_rpc_for_inprocess_master = 1;`\n\n\u003cbr /\u003e"]]
