KernelDefOrBuilder

общедоступный интерфейс KernelDefOrBuilder
Известные косвенные подклассы

Публичные методы

абстрактный KernelDef.AttrConstraint
getConstraint (индекс целого числа)
repeated .tensorflow.KernelDef.AttrConstraint constraint = 3;
абстрактный интервал
getConstraintCount ()
repeated .tensorflow.KernelDef.AttrConstraint constraint = 3;
абстрактный список < KernelDef.AttrConstraint >
getConstraintList ()
repeated .tensorflow.KernelDef.AttrConstraint constraint = 3;
абстрактный KernelDef.AttrConstraintOrBuilder
getConstraintOrBuilder (индекс целого числа)
repeated .tensorflow.KernelDef.AttrConstraint constraint = 3;
абстрактный список<? расширяет KernelDef.AttrConstraintOrBuilder >
getConstraintOrBuilderList ()
repeated .tensorflow.KernelDef.AttrConstraint constraint = 3;
абстрактная строка
getDeviceType () 
 Type of device this kernel runs on.
абстрактный com.google.protobuf.ByteString
getDeviceTypeBytes () 
 Type of device this kernel runs on.
абстрактная строка
getHostMemoryArg (индекс целого числа) 
 Names of the Op's input_/output_args that reside in host memory
 instead of device memory.
абстрактный com.google.protobuf.ByteString
getHostMemoryArgBytes (индекс целого числа) 
 Names of the Op's input_/output_args that reside in host memory
 instead of device memory.
абстрактный интервал
getHostMemoryArgCount () 
 Names of the Op's input_/output_args that reside in host memory
 instead of device memory.
абстрактный список<String>
getHostMemoryArgList () 
 Names of the Op's input_/output_args that reside in host memory
 instead of device memory.
абстрактная строка
получить метку () 
 This allows experimental kernels to be registered for an op that
 won't be used unless the user specifies a "_kernel" attr with
 value matching this.
абстрактный com.google.protobuf.ByteString
getLabelBytes () 
 This allows experimental kernels to be registered for an op that
 won't be used unless the user specifies a "_kernel" attr with
 value matching this.
абстрактная строка
получитьОп () 
 Must match the name of an Op.
абстрактный com.google.protobuf.ByteString
getOpBytes () 
 Must match the name of an Op.
абстрактный интервал
получить приоритет () 
 Prioritization of kernel amongst different devices.

Публичные методы

публичный абстрактный KernelDef.AttrConstraint getConstraint (индекс int)

repeated .tensorflow.KernelDef.AttrConstraint constraint = 3;

публичный абстрактный int getConstraintCount ()

repeated .tensorflow.KernelDef.AttrConstraint constraint = 3;

общедоступный абстрактный список < KernelDef.AttrConstraint > getConstraintList ()

repeated .tensorflow.KernelDef.AttrConstraint constraint = 3;

публичный абстрактный KernelDef.AttrConstraintOrBuilder getConstraintOrBuilder (индекс int)

repeated .tensorflow.KernelDef.AttrConstraint constraint = 3;

публичный абстрактный список<? расширяет KernelDef.AttrConstraintOrBuilder > getConstraintOrBuilderList ()

repeated .tensorflow.KernelDef.AttrConstraint constraint = 3;

общедоступная абстрактная строка getDeviceType () 

 Type of device this kernel runs on.
string device_type = 2;

общедоступный абстрактный com.google.protobuf.ByteString getDeviceTypeBytes () 

 Type of device this kernel runs on.
string device_type = 2;

общедоступная абстрактная строка getHostMemoryArg (индекс int) 

 Names of the Op's input_/output_args that reside in host memory
 instead of device memory.
repeated string host_memory_arg = 4;

общедоступный абстрактный com.google.protobuf.ByteString getHostMemoryArgBytes (индекс int) 

 Names of the Op's input_/output_args that reside in host memory
 instead of device memory.
repeated string host_memory_arg = 4;

общедоступный абстрактный int getHostMemoryArgCount () 

 Names of the Op's input_/output_args that reside in host memory
 instead of device memory.
repeated string host_memory_arg = 4;

общедоступный абстрактный список <String> getHostMemoryArgList () 

 Names of the Op's input_/output_args that reside in host memory
 instead of device memory.
repeated string host_memory_arg = 4;

общедоступная абстрактная строка getLabel () 

 This allows experimental kernels to be registered for an op that
 won't be used unless the user specifies a "_kernel" attr with
 value matching this.
string label = 5;

публичный абстрактный com.google.protobuf.ByteString getLabelBytes () 

 This allows experimental kernels to be registered for an op that
 won't be used unless the user specifies a "_kernel" attr with
 value matching this.
string label = 5;

общедоступная абстрактная строка getOp () 

 Must match the name of an Op.
string op = 1;

публичный абстрактный com.google.protobuf.ByteString getOpBytes () 

 Must match the name of an Op.
string op = 1;

публичный абстрактный int getPriority () 

 Prioritization of kernel amongst different devices. By default we assume
 priority is 0. The higher the priority the better. By default (i.e. if
 this is not set), we prefer GPU kernels over CPU.
int32 priority = 6;