CallableOptions.Builder

kelas akhir statis publik CallableOptions.Builder

 Defines a subgraph in another `GraphDef` as a set of feed points and nodes
 to be fetched or executed.
 Compare with the arguments to `Session::Run()`.
Protobuf tipe tensorflow.CallableOptions

Metode Publik

CallableOptions.Builder
addAllFeed (nilai<String> yang dapat diubah)
 Tensors to be fed in the callable.
CallableOptions.Builder
addAllFetch (nilai<String> yang dapat diubah)
 Fetches.
CallableOptions.Builder
addAllTarget (nilai<String> yang dapat diubah)
 Target Nodes.
CallableOptions.Builder
addAllTensorConnection (Nilai Iterable<? extends TensorConnection >)
 Tensors to be connected in the callable.
CallableOptions.Builder
addFeed (Nilai string)
 Tensors to be fed in the callable.
CallableOptions.Builder
addFeedBytes (nilai com.google.protobuf.ByteString)
 Tensors to be fed in the callable.
CallableOptions.Builder
addFetch (Nilai string)
 Fetches.
CallableOptions.Builder
addFetchBytes (nilai com.google.protobuf.ByteString)
 Fetches.
CallableOptions.Builder
addRepeatedField (bidang com.google.protobuf.Descriptors.FieldDescriptor, Nilai objek)
CallableOptions.Builder
addTarget (Nilai string)
 Target Nodes.
CallableOptions.Builder
addTargetBytes (nilai com.google.protobuf.ByteString)
 Target Nodes.
CallableOptions.Builder
addTensorConnection (indeks int, nilai TensorConnection )
 Tensors to be connected in the callable.
CallableOptions.Builder
addTensorConnection (indeks int, TensorConnection.Builder builderForValue)
 Tensors to be connected in the callable.
CallableOptions.Builder
addTensorConnection (nilai TensorConnection )
 Tensors to be connected in the callable.
CallableOptions.Builder
addTensorConnection ( TensorConnection.Builder builderForValue)
 Tensors to be connected in the callable.
TensorConnection.Builder
tambahkanTensorConnectionBuilder ()
 Tensors to be connected in the callable.
TensorConnection.Builder
addTensorConnectionBuilder (indeks int)
 Tensors to be connected in the callable.
Opsi yang Dapat Dipanggil
membangun ()
Opsi yang Dapat Dipanggil
membangunPartial ()
CallableOptions.Builder
jernih ()
CallableOptions.Builder
hapus Umpan ()
 Tensors to be fed in the callable.
CallableOptions.Builder
hapusPerangkat Umpan ()
CallableOptions.Builder
hapusAmbil ()
 Fetches.
CallableOptions.Builder
hapusFetchDevices ()
CallableOptions.Builder
hapusFetchSkipSync ()
 By default, RunCallable() will synchronize the GPU stream before returning
 fetched tensors on a GPU device, to ensure that the values in those tensors
 have been produced.
CallableOptions.Builder
clearField (bidang com.google.protobuf.Descriptors.FieldDescriptor)
CallableOptions.Builder
clearOneof (com.google.protobuf.Descriptors.OneofDescriptor salah satu)
CallableOptions.Builder
hapusRunOptions ()
 Options that will be applied to each run.
CallableOptions.Builder
hapus Target ()
 Target Nodes.
CallableOptions.Builder
hapusTensorConnection ()
 Tensors to be connected in the callable.
CallableOptions.Builder
klon ()
boolean
berisiFeedDevices (kunci string)
 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
boolean
berisiFetchDevices (kunci string)
map<string, string> fetch_devices = 7;
Opsi yang Dapat Dipanggil
dapatkanDefaultInstanceForType ()
com.google.protobuf.Descriptors.Descriptor statis terakhir
dapatkanDescriptor ()
com.google.protobuf.Descriptors.Descriptor
dapatkanDescriptorForType ()
Rangkaian
getFeed (indeks int)
 Tensors to be fed in the callable.
com.google.protobuf.ByteString
getFeedBytes (indeks int)
 Tensors to be fed in the callable.
ke dalam
dapatkan Jumlah Umpan ()
 Tensors to be fed in the callable.
Peta<String, String>
dapatkan Perangkat Umpan ()
Gunakan getFeedDevicesMap() sebagai gantinya.
ke dalam
dapatkanFeedDevicesCount ()
 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
Peta<String, String>
dapatkan FeedDevicesMap ()
 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
Rangkaian
getFeedDevicesOrDefault (kunci string, String defaultValue)
 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
Rangkaian
getFeedDevicesOrThrow (kunci string)
 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
com.google.protobuf.ProtocolStringList
dapatkanDaftar Umpan ()
 Tensors to be fed in the callable.
Rangkaian
getFetch (indeks int)
 Fetches.
com.google.protobuf.ByteString
getFetchBytes (indeks int)
 Fetches.
ke dalam
dapatkanFetchCount ()
 Fetches.
Peta<String, String>
dapatkanFetchDevices ()
Gunakan getFetchDevicesMap() sebagai gantinya.
ke dalam
dapatkanFetchDevicesCount ()
map<string, string> fetch_devices = 7;
Peta<String, String>
dapatkanFetchDevicesMap ()
map<string, string> fetch_devices = 7;
Rangkaian
getFetchDevicesOrDefault (kunci string, String defaultValue)
map<string, string> fetch_devices = 7;
Rangkaian
getFetchDevicesOrThrow (kunci string)
map<string, string> fetch_devices = 7;
com.google.protobuf.ProtocolStringList
dapatkanFetchList ()
 Fetches.
boolean
dapatkanFetchSkipSync ()
 By default, RunCallable() will synchronize the GPU stream before returning
 fetched tensors on a GPU device, to ensure that the values in those tensors
 have been produced.
Peta<String, String>
getMutableFeedDevices ()
Gunakan pengakses mutasi alternatif sebagai gantinya.
Peta<String, String>
getMutableFetchDevices ()
Gunakan pengakses mutasi alternatif sebagai gantinya.
Opsi Jalankan
dapatkan Opsi Jalankan ()
 Options that will be applied to each run.
JalankanOptions.Builder
dapatkanRunOptionsBuilder ()
 Options that will be applied to each run.
JalankanOptionsOrBuilder
dapatkanRunOptionsOrBuilder ()
 Options that will be applied to each run.
Rangkaian
getTarget (indeks int)
 Target Nodes.
com.google.protobuf.ByteString
getTargetBytes (indeks int)
 Target Nodes.
ke dalam
dapatkanTargetCount ()
 Target Nodes.
com.google.protobuf.ProtocolStringList
dapatkanDaftar Target ()
 Target Nodes.
Koneksi Tensor
getTensorConnection (indeks int)
 Tensors to be connected in the callable.
TensorConnection.Builder
getTensorConnectionBuilder (indeks int)
 Tensors to be connected in the callable.
Daftar< TensorConnection.Builder >
dapatkanTensorConnectionBuilderList ()
 Tensors to be connected in the callable.
ke dalam
dapatkanTensorConnectionCount ()
 Tensors to be connected in the callable.
Daftar< TensorConnection >
dapatkanTensorConnectionList ()
 Tensors to be connected in the callable.
TensorConnectionOrBuilder
getTensorConnectionOrBuilder (indeks int)
 Tensors to be connected in the callable.
Daftar<? memperluas TensorConnectionOrBuilder >
dapatkanTensorConnectionOrBuilderList ()
 Tensors to be connected in the callable.
boolean
hasRunOptions ()
 Options that will be applied to each run.
boolean terakhir
diinisialisasi ()
CallableOptions.Builder
mergeFrom (com.google.protobuf.Pesan lainnya)
CallableOptions.Builder
mergeFrom (com.google.protobuf.CodedInputStream masukan, com.google.protobuf.ExtensionRegistryLite extensionRegistry)
CallableOptions.Builder
mergeRunOptions (nilai RunOptions )
 Options that will be applied to each run.
CallableOptions.Builder terakhir
mergeUnknownFields (com.google.protobuf.UnknownFieldSet unknownFields)
CallableOptions.Builder
putAllFeedDevices (nilai Peta<String, String>)
 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
CallableOptions.Builder
putAllFetchDevices (nilai Peta<String, String>)
map<string, string> fetch_devices = 7;
CallableOptions.Builder
putFeedDevices (Kunci string, nilai String)
 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
CallableOptions.Builder
putFetchDevices (Kunci string, nilai String)
map<string, string> fetch_devices = 7;
CallableOptions.Builder
hapusFeedDevices (kunci string)
 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
CallableOptions.Builder
hapusFetchDevices (kunci string)
map<string, string> fetch_devices = 7;
CallableOptions.Builder
hapusTensorConnection (indeks int)
 Tensors to be connected in the callable.
CallableOptions.Builder
setFeed (indeks int, nilai String)
 Tensors to be fed in the callable.
CallableOptions.Builder
setFetch (indeks int, nilai String)
 Fetches.
CallableOptions.Builder
setFetchSkipSync (nilai boolean)
 By default, RunCallable() will synchronize the GPU stream before returning
 fetched tensors on a GPU device, to ensure that the values in those tensors
 have been produced.
CallableOptions.Builder
setField (bidang com.google.protobuf.Descriptors.FieldDescriptor, Nilai objek)
CallableOptions.Builder
setRepeatedField (bidang com.google.protobuf.Descriptors.FieldDescriptor, indeks int, Nilai objek)
CallableOptions.Builder
setRunOptions ( RunOptions.Pembuat pembangunForValue)
 Options that will be applied to each run.
CallableOptions.Builder
setRunOptions (nilai RunOptions )
 Options that will be applied to each run.
CallableOptions.Builder
setTarget (indeks int, nilai String)
 Target Nodes.
CallableOptions.Builder
setTensorConnection (indeks int, nilai TensorConnection )
 Tensors to be connected in the callable.
CallableOptions.Builder
setTensorConnection (indeks int, TensorConnection.Builder builderForValue)
 Tensors to be connected in the callable.
CallableOptions.Builder terakhir
setUnknownFields (com.google.protobuf.UnknownFieldSet unknownFields)

Metode Warisan

Metode Publik

CallableOptions.Builder addAllFeed publik (nilai<String> Iterable) 

 Tensors to be fed in the callable. Each feed is the name of a tensor.
repeated string feed = 1;

CallableOptions.Builder addAllFetch publik (nilai<String> Iterable) 

 Fetches. A list of tensor names. The caller of the callable expects a
 tensor to be returned for each fetch[i] (see RunStepResponse.tensor). The
 order of specified fetches does not change the execution order.
repeated string fetch = 2;

CallableOptions.Builder addAllTarget publik (nilai Iterable<String>) 

 Target Nodes. A list of node names. The named nodes will be run by the
 callable but their outputs will not be returned.
repeated string target = 3;

CallableOptions.Builder addAllTensorConnection publik (nilai Iterable<? extends TensorConnection >) 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

CallableOptions.Builder addFeed publik (Nilai string) 

 Tensors to be fed in the callable. Each feed is the name of a tensor.
repeated string feed = 1;

CallableOptions.Builder addFeedBytes publik (nilai com.google.protobuf.ByteString) 

 Tensors to be fed in the callable. Each feed is the name of a tensor.
repeated string feed = 1;

CallableOptions.Builder addFetch publik (Nilai string) 

 Fetches. A list of tensor names. The caller of the callable expects a
 tensor to be returned for each fetch[i] (see RunStepResponse.tensor). The
 order of specified fetches does not change the execution order.
repeated string fetch = 2;

CallableOptions.Builder addFetchBytes publik (nilai com.google.protobuf.ByteString) 

 Fetches. A list of tensor names. The caller of the callable expects a
 tensor to be returned for each fetch[i] (see RunStepResponse.tensor). The
 order of specified fetches does not change the execution order.
repeated string fetch = 2;

CallableOptions.Builder addRepeatedField publik (bidang com.google.protobuf.Descriptors.FieldDescriptor, Nilai objek)

CallableOptions.Builder addTarget publik (Nilai string) 

 Target Nodes. A list of node names. The named nodes will be run by the
 callable but their outputs will not be returned.
repeated string target = 3;

CallableOptions.Builder addTargetBytes publik (nilai com.google.protobuf.ByteString) 

 Target Nodes. A list of node names. The named nodes will be run by the
 callable but their outputs will not be returned.
repeated string target = 3;

CallableOptions.Builder addTensorConnection publik (indeks int, nilai TensorConnection ) 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

CallableOptions.Builder addTensorConnection publik (indeks int, TensorConnection.Builder builderForValue) 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

CallableOptions.Builder addTensorConnection publik (nilai TensorConnection ) 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

CallableOptions.Builder addTensorConnection publik ( TensorConnection.Builder builderForValue) 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

TensorConnection.Builder publik addTensorConnectionBuilder () 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

TensorConnection.Builder publik addTensorConnectionBuilder (indeks int) 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

build CallableOptions publik ()

buildPartial CallableOptions publik ()

CallableOptions.Builder publik jelas ()

CallableOptions publik.Builder clearFeed () 

 Tensors to be fed in the callable. Each feed is the name of a tensor.
repeated string feed = 1;

CallableOptions publik.Builder clearFeedDevices ()

CallableOptions publik.Builder clearFetch () 

 Fetches. A list of tensor names. The caller of the callable expects a
 tensor to be returned for each fetch[i] (see RunStepResponse.tensor). The
 order of specified fetches does not change the execution order.
repeated string fetch = 2;

CallableOptions publik.Builder clearFetchDevices ()

CallableOptions.Builder publik clearFetchSkipSync () 

 By default, RunCallable() will synchronize the GPU stream before returning
 fetched tensors on a GPU device, to ensure that the values in those tensors
 have been produced. This simplifies interacting with the tensors, but
 potentially incurs a performance hit.
 If this options is set to true, the caller is responsible for ensuring
 that the values in the fetched tensors have been produced before they are
 used. The caller can do this by invoking `Device::Sync()` on the underlying
 device(s), or by feeding the tensors back to the same Session using
 `feed_devices` with the same corresponding device name.
bool fetch_skip_sync = 8;

CallableOptions.Builder clearField publik (bidang com.google.protobuf.Descriptors.FieldDescriptor)

CallableOptions.Builder clearOneof publik (com.google.protobuf.Descriptors.OneofDescriptor oneof)

CallableOptions publik.Builder clearRunOptions () 

 Options that will be applied to each run.
.tensorflow.RunOptions run_options = 4;

CallableOptions publik.Builder clearTarget () 

 Target Nodes. A list of node names. The named nodes will be run by the
 callable but their outputs will not be returned.
repeated string target = 3;

CallableOptions publik.Builder clearTensorConnection () 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

klon CallableOptions.Builder publik ()

boolean publik berisiFeedDevices (kunci String) 

 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
 The options below allow changing that - feeding tensors backed by
 device memory, or returning tensors that are backed by device memory.
 The maps below map the name of a feed/fetch tensor (which appears in
 'feed' or 'fetch' fields above), to the fully qualified name of the device
 owning the memory backing the contents of the tensor.
 For example, creating a callable with the following options:
 CallableOptions {
   feed: "a:0"
   feed: "b:0"
   fetch: "x:0"
   fetch: "y:0"
   feed_devices: {
     "a:0": "/job:localhost/replica:0/task:0/device:GPU:0"
   }
   fetch_devices: {
     "y:0": "/job:localhost/replica:0/task:0/device:GPU:0"
  }
 }
 means that the Callable expects:
 - The first argument ("a:0") is a Tensor backed by GPU memory.
 - The second argument ("b:0") is a Tensor backed by host memory.
 and of its return values:
 - The first output ("x:0") will be backed by host memory.
 - The second output ("y:0") will be backed by GPU memory.
 FEEDS:
 It is the responsibility of the caller to ensure that the memory of the fed
 tensors will be correctly initialized and synchronized before it is
 accessed by operations executed during the call to Session::RunCallable().
 This is typically ensured by using the TensorFlow memory allocators
 (Device::GetAllocator()) to create the Tensor to be fed.
 Alternatively, for CUDA-enabled GPU devices, this typically means that the
 operation that produced the contents of the tensor has completed, i.e., the
 CUDA stream has been synchronized (e.g., via cuCtxSynchronize() or
 cuStreamSynchronize()).
map<string, string> feed_devices = 6;

boolean publik berisiFetchDevices (kunci string)

map<string, string> fetch_devices = 7;

CallableOptions publik getDefaultInstanceForType ()

public static final com.google.protobuf.Descriptors.Descriptor getDescriptor ()

com.google.protobuf.Descriptors.Descriptor publik getDescriptorForType ()

GetFeed String publik (indeks int) 

 Tensors to be fed in the callable. Each feed is the name of a tensor.
repeated string feed = 1;

com.google.protobuf.ByteString getFeedBytes publik (indeks int) 

 Tensors to be fed in the callable. Each feed is the name of a tensor.
repeated string feed = 1;

int publik getFeedCount () 

 Tensors to be fed in the callable. Each feed is the name of a tensor.
repeated string feed = 1;

Peta publik<String, String> getFeedDevices ()

Gunakan getFeedDevicesMap() sebagai gantinya.

int publik getFeedDevicesCount () 

 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
 The options below allow changing that - feeding tensors backed by
 device memory, or returning tensors that are backed by device memory.
 The maps below map the name of a feed/fetch tensor (which appears in
 'feed' or 'fetch' fields above), to the fully qualified name of the device
 owning the memory backing the contents of the tensor.
 For example, creating a callable with the following options:
 CallableOptions {
   feed: "a:0"
   feed: "b:0"
   fetch: "x:0"
   fetch: "y:0"
   feed_devices: {
     "a:0": "/job:localhost/replica:0/task:0/device:GPU:0"
   }
   fetch_devices: {
     "y:0": "/job:localhost/replica:0/task:0/device:GPU:0"
  }
 }
 means that the Callable expects:
 - The first argument ("a:0") is a Tensor backed by GPU memory.
 - The second argument ("b:0") is a Tensor backed by host memory.
 and of its return values:
 - The first output ("x:0") will be backed by host memory.
 - The second output ("y:0") will be backed by GPU memory.
 FEEDS:
 It is the responsibility of the caller to ensure that the memory of the fed
 tensors will be correctly initialized and synchronized before it is
 accessed by operations executed during the call to Session::RunCallable().
 This is typically ensured by using the TensorFlow memory allocators
 (Device::GetAllocator()) to create the Tensor to be fed.
 Alternatively, for CUDA-enabled GPU devices, this typically means that the
 operation that produced the contents of the tensor has completed, i.e., the
 CUDA stream has been synchronized (e.g., via cuCtxSynchronize() or
 cuStreamSynchronize()).
map<string, string> feed_devices = 6;

peta publik<String, String> getFeedDevicesMap () 

 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
 The options below allow changing that - feeding tensors backed by
 device memory, or returning tensors that are backed by device memory.
 The maps below map the name of a feed/fetch tensor (which appears in
 'feed' or 'fetch' fields above), to the fully qualified name of the device
 owning the memory backing the contents of the tensor.
 For example, creating a callable with the following options:
 CallableOptions {
   feed: "a:0"
   feed: "b:0"
   fetch: "x:0"
   fetch: "y:0"
   feed_devices: {
     "a:0": "/job:localhost/replica:0/task:0/device:GPU:0"
   }
   fetch_devices: {
     "y:0": "/job:localhost/replica:0/task:0/device:GPU:0"
  }
 }
 means that the Callable expects:
 - The first argument ("a:0") is a Tensor backed by GPU memory.
 - The second argument ("b:0") is a Tensor backed by host memory.
 and of its return values:
 - The first output ("x:0") will be backed by host memory.
 - The second output ("y:0") will be backed by GPU memory.
 FEEDS:
 It is the responsibility of the caller to ensure that the memory of the fed
 tensors will be correctly initialized and synchronized before it is
 accessed by operations executed during the call to Session::RunCallable().
 This is typically ensured by using the TensorFlow memory allocators
 (Device::GetAllocator()) to create the Tensor to be fed.
 Alternatively, for CUDA-enabled GPU devices, this typically means that the
 operation that produced the contents of the tensor has completed, i.e., the
 CUDA stream has been synchronized (e.g., via cuCtxSynchronize() or
 cuStreamSynchronize()).
map<string, string> feed_devices = 6;

String publik getFeedDevicesOrDefault (kunci string, String defaultValue) 

 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
 The options below allow changing that - feeding tensors backed by
 device memory, or returning tensors that are backed by device memory.
 The maps below map the name of a feed/fetch tensor (which appears in
 'feed' or 'fetch' fields above), to the fully qualified name of the device
 owning the memory backing the contents of the tensor.
 For example, creating a callable with the following options:
 CallableOptions {
   feed: "a:0"
   feed: "b:0"
   fetch: "x:0"
   fetch: "y:0"
   feed_devices: {
     "a:0": "/job:localhost/replica:0/task:0/device:GPU:0"
   }
   fetch_devices: {
     "y:0": "/job:localhost/replica:0/task:0/device:GPU:0"
  }
 }
 means that the Callable expects:
 - The first argument ("a:0") is a Tensor backed by GPU memory.
 - The second argument ("b:0") is a Tensor backed by host memory.
 and of its return values:
 - The first output ("x:0") will be backed by host memory.
 - The second output ("y:0") will be backed by GPU memory.
 FEEDS:
 It is the responsibility of the caller to ensure that the memory of the fed
 tensors will be correctly initialized and synchronized before it is
 accessed by operations executed during the call to Session::RunCallable().
 This is typically ensured by using the TensorFlow memory allocators
 (Device::GetAllocator()) to create the Tensor to be fed.
 Alternatively, for CUDA-enabled GPU devices, this typically means that the
 operation that produced the contents of the tensor has completed, i.e., the
 CUDA stream has been synchronized (e.g., via cuCtxSynchronize() or
 cuStreamSynchronize()).
map<string, string> feed_devices = 6;

String publik getFeedDevicesOrThrow (kunci String) 

 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
 The options below allow changing that - feeding tensors backed by
 device memory, or returning tensors that are backed by device memory.
 The maps below map the name of a feed/fetch tensor (which appears in
 'feed' or 'fetch' fields above), to the fully qualified name of the device
 owning the memory backing the contents of the tensor.
 For example, creating a callable with the following options:
 CallableOptions {
   feed: "a:0"
   feed: "b:0"
   fetch: "x:0"
   fetch: "y:0"
   feed_devices: {
     "a:0": "/job:localhost/replica:0/task:0/device:GPU:0"
   }
   fetch_devices: {
     "y:0": "/job:localhost/replica:0/task:0/device:GPU:0"
  }
 }
 means that the Callable expects:
 - The first argument ("a:0") is a Tensor backed by GPU memory.
 - The second argument ("b:0") is a Tensor backed by host memory.
 and of its return values:
 - The first output ("x:0") will be backed by host memory.
 - The second output ("y:0") will be backed by GPU memory.
 FEEDS:
 It is the responsibility of the caller to ensure that the memory of the fed
 tensors will be correctly initialized and synchronized before it is
 accessed by operations executed during the call to Session::RunCallable().
 This is typically ensured by using the TensorFlow memory allocators
 (Device::GetAllocator()) to create the Tensor to be fed.
 Alternatively, for CUDA-enabled GPU devices, this typically means that the
 operation that produced the contents of the tensor has completed, i.e., the
 CUDA stream has been synchronized (e.g., via cuCtxSynchronize() or
 cuStreamSynchronize()).
map<string, string> feed_devices = 6;

com.google.protobuf.ProtocolStringList getFeedList () publik 

 Tensors to be fed in the callable. Each feed is the name of a tensor.
repeated string feed = 1;

GetFetch String publik (indeks int) 

 Fetches. A list of tensor names. The caller of the callable expects a
 tensor to be returned for each fetch[i] (see RunStepResponse.tensor). The
 order of specified fetches does not change the execution order.
repeated string fetch = 2;

publik com.google.protobuf.ByteString getFetchBytes (indeks int) 

 Fetches. A list of tensor names. The caller of the callable expects a
 tensor to be returned for each fetch[i] (see RunStepResponse.tensor). The
 order of specified fetches does not change the execution order.
repeated string fetch = 2;

int publik getFetchCount () 

 Fetches. A list of tensor names. The caller of the callable expects a
 tensor to be returned for each fetch[i] (see RunStepResponse.tensor). The
 order of specified fetches does not change the execution order.
repeated string fetch = 2;

peta publik<String, String> getFetchDevices ()

Gunakan getFetchDevicesMap() sebagai gantinya.

int publik getFetchDevicesCount ()

map<string, string> fetch_devices = 7;

Peta publik<String, String> getFetchDevicesMap ()

map<string, string> fetch_devices = 7;

String publik getFetchDevicesOrDefault (kunci string, String defaultValue)

map<string, string> fetch_devices = 7;

String publik getFetchDevicesOrThrow (kunci String)

map<string, string> fetch_devices = 7;

com.google.protobuf.ProtocolStringList getFetchList () publik 

 Fetches. A list of tensor names. The caller of the callable expects a
 tensor to be returned for each fetch[i] (see RunStepResponse.tensor). The
 order of specified fetches does not change the execution order.
repeated string fetch = 2;

getFetchSkipSync boolean publik () 

 By default, RunCallable() will synchronize the GPU stream before returning
 fetched tensors on a GPU device, to ensure that the values in those tensors
 have been produced. This simplifies interacting with the tensors, but
 potentially incurs a performance hit.
 If this options is set to true, the caller is responsible for ensuring
 that the values in the fetched tensors have been produced before they are
 used. The caller can do this by invoking `Device::Sync()` on the underlying
 device(s), or by feeding the tensors back to the same Session using
 `feed_devices` with the same corresponding device name.
bool fetch_skip_sync = 8;

peta publik<String, String> getMutableFeedDevices ()

Gunakan pengakses mutasi alternatif sebagai gantinya.

Peta publik<String, String> getMutableFetchDevices ()

Gunakan pengakses mutasi alternatif sebagai gantinya.

RunOptions publik getRunOptions () 

 Options that will be applied to each run.
.tensorflow.RunOptions run_options = 4;

RunOptions.Builder publik getRunOptionsBuilder () 

 Options that will be applied to each run.
.tensorflow.RunOptions run_options = 4;

RunOptionsOrBuilder publik getRunOptionsOrBuilder () 

 Options that will be applied to each run.
.tensorflow.RunOptions run_options = 4;

GetTarget String publik (indeks int) 

 Target Nodes. A list of node names. The named nodes will be run by the
 callable but their outputs will not be returned.
repeated string target = 3;

publik com.google.protobuf.ByteString getTargetBytes (indeks int) 

 Target Nodes. A list of node names. The named nodes will be run by the
 callable but their outputs will not be returned.
repeated string target = 3;

int publik getTargetCount () 

 Target Nodes. A list of node names. The named nodes will be run by the
 callable but their outputs will not be returned.
repeated string target = 3;

com.google.protobuf.ProtocolStringList getTargetList () publik 

 Target Nodes. A list of node names. The named nodes will be run by the
 callable but their outputs will not be returned.
repeated string target = 3;

TensorConnection publik getTensorConnection (indeks int) 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

TensorConnection.Builder publik getTensorConnectionBuilder (int indeks) 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

Daftar publik< TensorConnection.Builder > getTensorConnectionBuilderList () 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

int publik getTensorConnectionCount () 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

Daftar publik< TensorConnection > getTensorConnectionList () 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

TensorConnectionOrBuilder publik getTensorConnectionOrBuilder (int indeks) 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

Daftar Publik<? memperluas TensorConnectionOrBuilder > getTensorConnectionOrBuilderList () 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

boolean publik hasRunOptions () 

 Options that will be applied to each run.
.tensorflow.RunOptions run_options = 4;

boolean akhir publik diinisialisasi ()

CallableOptions.Builder mergeFrom publik (com.google.protobuf.Message lainnya)

CallableOptions.Builder mergeFrom publik (com.google.protobuf.CodedInputStream masukan, com.google.protobuf.ExtensionRegistryLite extensionRegistry)

Melempar
Pengecualian IO

CallableOptions.Builder mergeRunOptions publik (nilai RunOptions ) 

 Options that will be applied to each run.
.tensorflow.RunOptions run_options = 4;

CallableOptions.Builder final publik menggabungkanUnknownFields (com.google.protobuf.UnknownFieldSet unknownFields)

CallableOptions.Builder putAllFeedDevices publik (nilai Peta<String, String>) 

 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
 The options below allow changing that - feeding tensors backed by
 device memory, or returning tensors that are backed by device memory.
 The maps below map the name of a feed/fetch tensor (which appears in
 'feed' or 'fetch' fields above), to the fully qualified name of the device
 owning the memory backing the contents of the tensor.
 For example, creating a callable with the following options:
 CallableOptions {
   feed: "a:0"
   feed: "b:0"
   fetch: "x:0"
   fetch: "y:0"
   feed_devices: {
     "a:0": "/job:localhost/replica:0/task:0/device:GPU:0"
   }
   fetch_devices: {
     "y:0": "/job:localhost/replica:0/task:0/device:GPU:0"
  }
 }
 means that the Callable expects:
 - The first argument ("a:0") is a Tensor backed by GPU memory.
 - The second argument ("b:0") is a Tensor backed by host memory.
 and of its return values:
 - The first output ("x:0") will be backed by host memory.
 - The second output ("y:0") will be backed by GPU memory.
 FEEDS:
 It is the responsibility of the caller to ensure that the memory of the fed
 tensors will be correctly initialized and synchronized before it is
 accessed by operations executed during the call to Session::RunCallable().
 This is typically ensured by using the TensorFlow memory allocators
 (Device::GetAllocator()) to create the Tensor to be fed.
 Alternatively, for CUDA-enabled GPU devices, this typically means that the
 operation that produced the contents of the tensor has completed, i.e., the
 CUDA stream has been synchronized (e.g., via cuCtxSynchronize() or
 cuStreamSynchronize()).
map<string, string> feed_devices = 6;

CallableOptions.Builder putAllFetchDevices publik (nilai Peta<String, String>)

map<string, string> fetch_devices = 7;

CallableOptions.Builder putFeedDevices publik (kunci string, nilai string) 

 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
 The options below allow changing that - feeding tensors backed by
 device memory, or returning tensors that are backed by device memory.
 The maps below map the name of a feed/fetch tensor (which appears in
 'feed' or 'fetch' fields above), to the fully qualified name of the device
 owning the memory backing the contents of the tensor.
 For example, creating a callable with the following options:
 CallableOptions {
   feed: "a:0"
   feed: "b:0"
   fetch: "x:0"
   fetch: "y:0"
   feed_devices: {
     "a:0": "/job:localhost/replica:0/task:0/device:GPU:0"
   }
   fetch_devices: {
     "y:0": "/job:localhost/replica:0/task:0/device:GPU:0"
  }
 }
 means that the Callable expects:
 - The first argument ("a:0") is a Tensor backed by GPU memory.
 - The second argument ("b:0") is a Tensor backed by host memory.
 and of its return values:
 - The first output ("x:0") will be backed by host memory.
 - The second output ("y:0") will be backed by GPU memory.
 FEEDS:
 It is the responsibility of the caller to ensure that the memory of the fed
 tensors will be correctly initialized and synchronized before it is
 accessed by operations executed during the call to Session::RunCallable().
 This is typically ensured by using the TensorFlow memory allocators
 (Device::GetAllocator()) to create the Tensor to be fed.
 Alternatively, for CUDA-enabled GPU devices, this typically means that the
 operation that produced the contents of the tensor has completed, i.e., the
 CUDA stream has been synchronized (e.g., via cuCtxSynchronize() or
 cuStreamSynchronize()).
map<string, string> feed_devices = 6;

CallableOptions.Builder putFetchDevices publik (kunci string, nilai string)

map<string, string> fetch_devices = 7;

CallableOptions.Builder publik menghapusFeedDevices (kunci String) 

 The Tensor objects fed in the callable and fetched from the callable
 are expected to be backed by host (CPU) memory by default.
 The options below allow changing that - feeding tensors backed by
 device memory, or returning tensors that are backed by device memory.
 The maps below map the name of a feed/fetch tensor (which appears in
 'feed' or 'fetch' fields above), to the fully qualified name of the device
 owning the memory backing the contents of the tensor.
 For example, creating a callable with the following options:
 CallableOptions {
   feed: "a:0"
   feed: "b:0"
   fetch: "x:0"
   fetch: "y:0"
   feed_devices: {
     "a:0": "/job:localhost/replica:0/task:0/device:GPU:0"
   }
   fetch_devices: {
     "y:0": "/job:localhost/replica:0/task:0/device:GPU:0"
  }
 }
 means that the Callable expects:
 - The first argument ("a:0") is a Tensor backed by GPU memory.
 - The second argument ("b:0") is a Tensor backed by host memory.
 and of its return values:
 - The first output ("x:0") will be backed by host memory.
 - The second output ("y:0") will be backed by GPU memory.
 FEEDS:
 It is the responsibility of the caller to ensure that the memory of the fed
 tensors will be correctly initialized and synchronized before it is
 accessed by operations executed during the call to Session::RunCallable().
 This is typically ensured by using the TensorFlow memory allocators
 (Device::GetAllocator()) to create the Tensor to be fed.
 Alternatively, for CUDA-enabled GPU devices, this typically means that the
 operation that produced the contents of the tensor has completed, i.e., the
 CUDA stream has been synchronized (e.g., via cuCtxSynchronize() or
 cuStreamSynchronize()).
map<string, string> feed_devices = 6;

CallableOptions.Builder publik deleteFetchDevices (kunci string)

map<string, string> fetch_devices = 7;

CallableOptions.Builder publik menghapusTensorConnection (int indeks) 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

CallableOptions.Builder setFeed publik (indeks int, nilai String) 

 Tensors to be fed in the callable. Each feed is the name of a tensor.
repeated string feed = 1;

CallableOptions.Builder setFetch publik (indeks int, nilai String) 

 Fetches. A list of tensor names. The caller of the callable expects a
 tensor to be returned for each fetch[i] (see RunStepResponse.tensor). The
 order of specified fetches does not change the execution order.
repeated string fetch = 2;

CallableOptions.Builder setFetchSkipSync publik (nilai boolean) 

 By default, RunCallable() will synchronize the GPU stream before returning
 fetched tensors on a GPU device, to ensure that the values in those tensors
 have been produced. This simplifies interacting with the tensors, but
 potentially incurs a performance hit.
 If this options is set to true, the caller is responsible for ensuring
 that the values in the fetched tensors have been produced before they are
 used. The caller can do this by invoking `Device::Sync()` on the underlying
 device(s), or by feeding the tensors back to the same Session using
 `feed_devices` with the same corresponding device name.
bool fetch_skip_sync = 8;

CallableOptions.Builder setField publik (bidang com.google.protobuf.Descriptors.FieldDescriptor, Nilai objek)

CallableOptions.Builder setRepeatedField publik (bidang com.google.protobuf.Descriptors.FieldDescriptor, indeks int, Nilai objek)

CallableOptions.Builder setRunOptions publik ( RunOptions.Builder builderForValue) 

 Options that will be applied to each run.
.tensorflow.RunOptions run_options = 4;

CallableOptions.Builder setRunOptions publik (nilai RunOptions ) 

 Options that will be applied to each run.
.tensorflow.RunOptions run_options = 4;

CallableOptions.Builder setTarget publik (indeks int, nilai String) 

 Target Nodes. A list of node names. The named nodes will be run by the
 callable but their outputs will not be returned.
repeated string target = 3;

CallableOptions.Builder setTensorConnection publik (indeks int, nilai TensorConnection ) 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

CallableOptions.Builder setTensorConnection publik (indeks int, TensorConnection.Builder builderForValue) 

 Tensors to be connected in the callable. Each TensorConnection denotes
 a pair of tensors in the graph, between which an edge will be created
 in the callable.
repeated .tensorflow.TensorConnection tensor_connection = 5;

CallableOptions.Builder setUnknownFields final publik (com.google.protobuf.UnknownFieldSet unknownFields)