RewriterConfig.Builder คลาสสุดท้ายแบบคงที่สาธารณะ
Graph rewriting is experimental and subject to change, not covered by any API stability guarantees.
tensorflow.RewriterConfig วิธีการสาธารณะ
| RewriterConfig.Builder | addAllCustomOptimizers (Iterable<? ขยาย RewriterConfig.CustomGraphOptimizer > ค่า) list of CustomGraphOptimizers to apply. |
| RewriterConfig.Builder | addAllOptimizers (ค่า Iterable<String>) If non-empty, will use this as an alternative way to specify a list of optimizations to turn on and the order of the optimizations (replacing the meta-optimizer). |
| RewriterConfig.Builder | addCustomOptimizers ( RewriterConfig.CustomGraphOptimizer.Builder builderForValue) list of CustomGraphOptimizers to apply. |
| RewriterConfig.Builder | addCustomOptimizers (ดัชนี int, RewriterConfig.CustomGraphOptimizer.Builder builderForValue) list of CustomGraphOptimizers to apply. |
| RewriterConfig.Builder | addCustomOptimizers (ค่า RewriterConfig.CustomGraphOptimizer ) list of CustomGraphOptimizers to apply. |
| RewriterConfig.Builder | addCustomOptimizers (ดัชนี int, ค่า RewriterConfig.CustomGraphOptimizer ) list of CustomGraphOptimizers to apply. |
| RewriterConfig.CustomGraphOptimizer.Builder | addCustomOptimizersBuilder (ดัชนี int) list of CustomGraphOptimizers to apply. |
| RewriterConfig.CustomGraphOptimizer.Builder | addCustomOptimizersBuilder () list of CustomGraphOptimizers to apply. |
| RewriterConfig.Builder | addOptimizers (ค่าสตริง) If non-empty, will use this as an alternative way to specify a list of optimizations to turn on and the order of the optimizations (replacing the meta-optimizer). |
| RewriterConfig.Builder | addOptimizersBytes (ค่า com.google.protobuf.ByteString) If non-empty, will use this as an alternative way to specify a list of optimizations to turn on and the order of the optimizations (replacing the meta-optimizer). |
| RewriterConfig.Builder | addRepeatedField (com.google.protobuf.Descriptors.FieldDescriptor ช่อง ค่าอ็อบเจ็กต์) |
| RewriterConfig | สร้าง () |
| RewriterConfig | สร้างบางส่วน () |
| RewriterConfig.Builder | ชัดเจน () |
| RewriterConfig.Builder | การเพิ่มประสิทธิภาพทางคณิตศาสตร์ที่ชัดเจน () Arithmetic optimizations (default is ON) e.g. |
| RewriterConfig.Builder | ล้างอัตโนมัติผสมความแม่นยำ () Optimize data types for CUDA (default is OFF). |
| RewriterConfig.Builder | clearAutoMixedPrecisionMkl () Optimize data types for MKL (default is OFF). |
| RewriterConfig.Builder | ล้างอัตโนมัติขนาน () Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field. |
| RewriterConfig.Builder | clearCommonSubgraphElimination () Common subgraph elimination (default is ON) e.g. |
| RewriterConfig.Builder | ชัดเจนคงที่พับ () Fold constants (default is ON) Statically infer the value of tensors when possible, and materialize the result using constants. |
| RewriterConfig.Builder | ล้าง CPULayoutConversion () CPU Conversion settings between NHCW and NCHW. |
| RewriterConfig.Builder | clearCustomOptimizers () list of CustomGraphOptimizers to apply. |
| RewriterConfig.Builder | clearDebugStripper () Strips debug-related nodes from the graph (off by default). |
| RewriterConfig.Builder | clearDependencyOptimization () Control dependency optimizations (default is ON). |
| RewriterConfig.Builder | clearDisableMetaOptimizer () Disable the entire meta optimizer (off by default). |
| RewriterConfig.Builder | clearDisableModelPruning () If true, don't remove unnecessary ops from the graph bool disable_model_pruning = 2; |
| RewriterConfig.Builder | clearExperimentalDisableCompressedTensorOptimization () Disable optimizations that assume compressed tensors. |
| RewriterConfig.Builder | clearFailOnOptimizerErrors () If true, any optimization pass failing will cause the MetaOptimizer to stop with an error. |
| RewriterConfig.Builder | clearField (ฟิลด์ com.google.protobuf.Descriptors.FieldDescriptor) |
| RewriterConfig.Builder | clearFunctionOptimization () Function optimizations (default is ON). |
| RewriterConfig.Builder | ตัวเลือกที่ชัดเจนการใช้งาน () Enable the swap of kernel implementations based on the device placement (default is ON). |
| RewriterConfig.Builder | clearInterOptimizerVerifierConfig () VerifierConfig specifying the verifiers to be run after every optimizer. |
| RewriterConfig.Builder | clearLayoutOptimizer () Optimize tensor layouts (default is ON) e.g. |
| RewriterConfig.Builder | การเพิ่มประสิทธิภาพ clearLoop () Loop optimizations (default is ON). |
| RewriterConfig.Builder | การเพิ่มประสิทธิภาพหน่วยความจำที่ชัดเจน () Configures memory optimization passes through the meta-optimizer. |
| RewriterConfig.Builder | clearMemoryOptimizerTargetNodeNameScope () A node name scope for node names which are valid outputs of recomputations. |
| RewriterConfig.Builder | clearMetaOptimizerIterations () Controls how many times we run the optimizers in meta optimizer (default is once). |
| RewriterConfig.Builder | clearMetaOptimizerTimeoutMs () Maximum number of milliseconds to spend optimizing a single graph before timing out. |
| RewriterConfig.Builder | clearMinGraphNodes () The minimum number of nodes in a graph to optimizer. |
| RewriterConfig.Builder | clearOneof (com.google.protobuf.Descriptors.OneofDescriptor oneof) |
| RewriterConfig.Builder | เครื่องมือเพิ่มประสิทธิภาพที่ชัดเจน () If non-empty, will use this as an alternative way to specify a list of optimizations to turn on and the order of the optimizations (replacing the meta-optimizer). |
| RewriterConfig.Builder | การเพิ่มประสิทธิภาพ clearPinToHost () Force small ops onto the CPU (default is OFF). |
| RewriterConfig.Builder | clearPostOptimizationVerifierConfig () VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run. |
| RewriterConfig.Builder | เคลียร์การแมป () Remapping (default is ON) Remap subgraphs onto more efficient implementations. |
| RewriterConfig.Builder | การเพิ่มประสิทธิภาพ clearScopedAllocator () Try to allocate some independent Op outputs contiguously in order to merge or eliminate downstream Ops (off by default). |
| RewriterConfig.Builder | clearScopedAllocatorOpts () .tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16; |
| RewriterConfig.Builder | การเพิ่มประสิทธิภาพรูปร่างที่ชัดเจน () Shape optimizations (default is ON) Simplify computations made on shapes. |
| RewriterConfig.Builder | โคลน () |
| RewriterConfig.สลับ | getArithmeticOptimization () Arithmetic optimizations (default is ON) e.g. |
| ภายใน | getArithmeticOptimizationValue () Arithmetic optimizations (default is ON) e.g. |
| RewriterConfig.สลับ | รับ AutoMixedPrecision () Optimize data types for CUDA (default is OFF). |
| RewriterConfig.สลับ | รับ AutoMixedPrecisionMkl () Optimize data types for MKL (default is OFF). |
| ภายใน | รับ AutoMixedPrecisionMklValue () Optimize data types for MKL (default is OFF). |
| ภายใน | รับ AutoMixedPrecisionValue () Optimize data types for CUDA (default is OFF). |
| ตัวเลือกขนานอัตโนมัติ | รับอัตโนมัติขนาน () Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field. |
| AutoParallelOptions.ตัวสร้าง | รับ AutoParallelBuilder () Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field. |
| AutoParallelOptionsOrBuilder | รับ AutoParallelOrBuilder () Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field. |
| RewriterConfig.สลับ | getCommonSubgraphElimination () Common subgraph elimination (default is ON) e.g. |
| ภายใน | getCommonSubgraphEliminationValue () Common subgraph elimination (default is ON) e.g. |
| RewriterConfig.สลับ | getConstantFolding () Fold constants (default is ON) Statically infer the value of tensors when possible, and materialize the result using constants. |
| ภายใน | getConstantFoldingValue () Fold constants (default is ON) Statically infer the value of tensors when possible, and materialize the result using constants. |
| RewriterConfig.CpuLayout | getCpuLayout การแปลง () CPU Conversion settings between NHCW and NCHW. |
| ภายใน | getCpuLayoutConversionValue () CPU Conversion settings between NHCW and NCHW. |
| RewriterConfig.CustomGraphOptimizer | getCustomOptimizers (ดัชนี int) list of CustomGraphOptimizers to apply. |
| RewriterConfig.CustomGraphOptimizer.Builder | getCustomOptimizersBuilder (ดัชนี int) list of CustomGraphOptimizers to apply. |
| รายการ < RewriterConfig.CustomGraphOptimizer.Builder > | getCustomOptimizersBuilderList () list of CustomGraphOptimizers to apply. |
| ภายใน | getCustomOptimizersCount () list of CustomGraphOptimizers to apply. |
| รายการ < RewriterConfig.CustomGraphOptimizer > | getCustomOptimizersList () list of CustomGraphOptimizers to apply. |
| RewriterConfig.CustomGraphOptimizerOrBuilder | getCustomOptimizersOrBuilder (ดัชนี int) list of CustomGraphOptimizers to apply. |
| รายการ<? ขยาย RewriterConfig.CustomGraphOptimizerOrBuilder > | getCustomOptimizersOrBuilderList () list of CustomGraphOptimizers to apply. |
| RewriterConfig.สลับ | getDebugStripper () Strips debug-related nodes from the graph (off by default). |
| ภายใน | getDebugStripperValue () Strips debug-related nodes from the graph (off by default). |
| RewriterConfig | |
| RewriterConfig.สลับ | getDependencyOptimization () Control dependency optimizations (default is ON). |
| ภายใน | getDependencyOptimizationValue () Control dependency optimizations (default is ON). |
| com.google.protobuf.Descriptors.Descriptor แบบคงที่ขั้นสุดท้าย | รับคำอธิบาย () |
| com.google.protobuf.Descriptors.Descriptor | |
| บูลีน | getDisableMetaOptimizer () Disable the entire meta optimizer (off by default). |
| บูลีน | getDisableModelPruning () If true, don't remove unnecessary ops from the graph bool disable_model_pruning = 2; |
| บูลีน | getExperimentalDisableCompressedTensorOptimization () Disable optimizations that assume compressed tensors. |
| บูลีน | getFailOnOptimizer ข้อผิดพลาด () If true, any optimization pass failing will cause the MetaOptimizer to stop with an error. |
| RewriterConfig.สลับ | getFunctionOptimization () Function optimizations (default is ON). |
| ภายใน | getFunctionOptimizationValue () Function optimizations (default is ON). |
| RewriterConfig.สลับ | getIlementationSelector () Enable the swap of kernel implementations based on the device placement (default is ON). |
| ภายใน | getImplementationSelectorValue () Enable the swap of kernel implementations based on the device placement (default is ON). |
| VerifierConfig | getInterOptimizerVerifierConfig () VerifierConfig specifying the verifiers to be run after every optimizer. |
| VerifierConfig.Builder | getInterOptimizerVerifierConfigBuilder () VerifierConfig specifying the verifiers to be run after every optimizer. |
| VerifierConfigOrBuilder | getInterOptimizerVerifierConfigOrBuilder () VerifierConfig specifying the verifiers to be run after every optimizer. |
| RewriterConfig.สลับ | getLayoutOptimizer () Optimize tensor layouts (default is ON) e.g. |
| ภายใน | getLayoutOptimizerValue () Optimize tensor layouts (default is ON) e.g. |
| RewriterConfig.สลับ | getLoopOptimization () Loop optimizations (default is ON). |
| ภายใน | getLoopOptimizationValue () Loop optimizations (default is ON). |
| RewriterConfig.MemOptType | getMemoryOptimization () Configures memory optimization passes through the meta-optimizer. |
| ภายใน | getMemoryOptimizationValue () Configures memory optimization passes through the meta-optimizer. |
| สตริง | getMemoryOptimizerTargetNodeNameScope () A node name scope for node names which are valid outputs of recomputations. |
| com.google.protobuf.ByteString | getMemoryOptimizerTargetNodeNameScopeBytes () A node name scope for node names which are valid outputs of recomputations. |
| RewriterConfig.NumIterationsType | getMetaOptimizerIterations () Controls how many times we run the optimizers in meta optimizer (default is once). |
| ภายใน | getMetaOptimizerIterationsValue () Controls how many times we run the optimizers in meta optimizer (default is once). |
| ยาว | getMetaOptimizerTimeoutMs () Maximum number of milliseconds to spend optimizing a single graph before timing out. |
| ภายใน | รับ MinGraphNodes () The minimum number of nodes in a graph to optimizer. |
| สตริง | getOptimizers (ดัชนี int) If non-empty, will use this as an alternative way to specify a list of optimizations to turn on and the order of the optimizations (replacing the meta-optimizer). |
| com.google.protobuf.ByteString | getOptimizersBytes (ดัชนี int) If non-empty, will use this as an alternative way to specify a list of optimizations to turn on and the order of the optimizations (replacing the meta-optimizer). |
| ภายใน | getOptimizersCount () If non-empty, will use this as an alternative way to specify a list of optimizations to turn on and the order of the optimizations (replacing the meta-optimizer). |
| com.google.protobuf.ProtocolStringList | getOptimizersList () If non-empty, will use this as an alternative way to specify a list of optimizations to turn on and the order of the optimizations (replacing the meta-optimizer). |
| RewriterConfig.สลับ | การเพิ่มประสิทธิภาพ getPinToHost () Force small ops onto the CPU (default is OFF). |
| ภายใน | getPinToHostOptimizationValue () Force small ops onto the CPU (default is OFF). |
| VerifierConfig | getPostOptimizationVerifierConfig () VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run. |
| VerifierConfig.Builder | getPostOptimizationVerifierConfigBuilder () VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run. |
| VerifierConfigOrBuilder | getPostOptimizationVerifierConfigOrBuilder () VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run. |
| RewriterConfig.สลับ | รับการแมป () Remapping (default is ON) Remap subgraphs onto more efficient implementations. |
| ภายใน | รับค่าการแมปใหม่ () Remapping (default is ON) Remap subgraphs onto more efficient implementations. |
| RewriterConfig.สลับ | การเพิ่มประสิทธิภาพ getScopedAllocator () Try to allocate some independent Op outputs contiguously in order to merge or eliminate downstream Ops (off by default). |
| ภายใน | getScopedAllocatorOptimizationValue () Try to allocate some independent Op outputs contiguously in order to merge or eliminate downstream Ops (off by default). |
| ตัวเลือกขอบเขต Allocator | getScopedAllocatorOpts () .tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16; |
| ScopedAllocatorOptions.Builder | getScopedAllocatorOptsBuilder () .tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16; |
| ScopedAllocatorOptionsOrBuilder | getScopedAllocatorOptsOrBuilder () .tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16; |
| RewriterConfig.สลับ | getShapeOptimization () Shape optimizations (default is ON) Simplify computations made on shapes. |
| ภายใน | getShapeOptimizationValue () Shape optimizations (default is ON) Simplify computations made on shapes. |
| บูลีน | มีอัตโนมัติขนาน () Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field. |
| บูลีน | hasInterOptimizerVerifierConfig () VerifierConfig specifying the verifiers to be run after every optimizer. |
| บูลีน | hasPostOptimizationVerifierConfig () VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run. |
| บูลีน | hasScopedAllocatorOpts () .tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16; |
| บูลีนสุดท้าย | |
| RewriterConfig.Builder | mergeAutoParallel (ค่า AutoParallelOptions ) Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field. |
| RewriterConfig.Builder | mergeFrom (com.google.protobuf.Message อื่น ๆ ) |
| RewriterConfig.Builder | mergeFrom (com.google.protobuf.CodedInputStream อินพุต com.google.protobuf.ExtensionRegistryLite extensionRegistry) |
| RewriterConfig.Builder | mergeInterOptimizerVerifierConfig (ค่า VerifierConfig ) VerifierConfig specifying the verifiers to be run after every optimizer. |
| RewriterConfig.Builder | mergePostOptimizationVerifierConfig (ค่า VerifierConfig ) VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run. |
| RewriterConfig.Builder | mergeScopedAllocatorOpts (ค่า ScopedAllocatorOptions ) .tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16; |
| RewriterConfig.Builder สุดท้าย | mergeUnknownFields (com.google.protobuf.UnknownFieldSetknownFields) |
| RewriterConfig.Builder | RemoveCustomOptimizers (ดัชนี int) list of CustomGraphOptimizers to apply. |
| RewriterConfig.Builder | setArithmeticOptimization (ค่า RewriterConfig.Toggle ) Arithmetic optimizations (default is ON) e.g. |
| RewriterConfig.Builder | setArithmeticOptimizationValue (ค่า int) Arithmetic optimizations (default is ON) e.g. |
| RewriterConfig.Builder | |
| RewriterConfig.Builder | |
| RewriterConfig.Builder | setAutoMixedPrecisionMklValue (ค่า int) Optimize data types for MKL (default is OFF). |
| RewriterConfig.Builder | setAutoMixedPrecisionValue (ค่า int) Optimize data types for CUDA (default is OFF). |
| RewriterConfig.Builder | setAutoParallel ( AutoParallelOptions.Builder builderForValue) Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field. |
| RewriterConfig.Builder | setAutoParallel (ค่า AutoParallelOptions ) Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field. |
| RewriterConfig.Builder | setCommonSubgraphElimination (ค่า RewriterConfig.Toggle ) Common subgraph elimination (default is ON) e.g. |
| RewriterConfig.Builder | setCommonSubgraphEliminationValue (ค่า int) Common subgraph elimination (default is ON) e.g. |
| RewriterConfig.Builder | setConstantFolding (ค่า RewriterConfig.Toggle ) Fold constants (default is ON) Statically infer the value of tensors when possible, and materialize the result using constants. |
| RewriterConfig.Builder | setConstantFoldingValue (ค่า int) Fold constants (default is ON) Statically infer the value of tensors when possible, and materialize the result using constants. |
| RewriterConfig.Builder | setCpuLayoutConversion (ค่า RewriterConfig.CpuLayout ) CPU Conversion settings between NHCW and NCHW. |
| RewriterConfig.Builder | setCpuLayoutConversionValue (ค่า int) CPU Conversion settings between NHCW and NCHW. |
| RewriterConfig.Builder | setCustomOptimizers (ดัชนี int, RewriterConfig.CustomGraphOptimizer.Builder builderForValue) list of CustomGraphOptimizers to apply. |
| RewriterConfig.Builder | setCustomOptimizers (ดัชนี int, ค่า RewriterConfig.CustomGraphOptimizer ) list of CustomGraphOptimizers to apply. |
| RewriterConfig.Builder | setDebugStripper (ค่า RewriterConfig.Toggle ) Strips debug-related nodes from the graph (off by default). |
| RewriterConfig.Builder | setDebugStripperValue (ค่า int) Strips debug-related nodes from the graph (off by default). |
| RewriterConfig.Builder | setDependencyOptimization (ค่า RewriterConfig.Toggle ) Control dependency optimizations (default is ON). |
| RewriterConfig.Builder | setDependencyOptimizationValue (ค่า int) Control dependency optimizations (default is ON). |
| RewriterConfig.Builder | setDisableMetaOptimizer (ค่าบูลีน) Disable the entire meta optimizer (off by default). |
| RewriterConfig.Builder | setDisableModelPruning (ค่าบูลีน) If true, don't remove unnecessary ops from the graph bool disable_model_pruning = 2; |
| RewriterConfig.Builder | setExperimentalDisableCompressedTensorOptimization (ค่าบูลีน) Disable optimizations that assume compressed tensors. |
| RewriterConfig.Builder | setFailOnOptimizerErrors (ค่าบูลีน) If true, any optimization pass failing will cause the MetaOptimizer to stop with an error. |
| RewriterConfig.Builder | setField (ฟิลด์ com.google.protobuf.Descriptors.FieldDescriptor ค่าอ็อบเจ็กต์) |
| RewriterConfig.Builder | |
| RewriterConfig.Builder | setFunctionOptimizationValue (ค่า int) Function optimizations (default is ON). |
| RewriterConfig.Builder | setImplementationSelector (ค่า RewriterConfig.Toggle ) Enable the swap of kernel implementations based on the device placement (default is ON). |
| RewriterConfig.Builder | setImplementationSelectorValue (ค่า int) Enable the swap of kernel implementations based on the device placement (default is ON). |
| RewriterConfig.Builder | setInterOptimizerVerifierConfig ( VerifierConfig.Builder builderForValue) VerifierConfig specifying the verifiers to be run after every optimizer. |
| RewriterConfig.Builder | setInterOptimizerVerifierConfig (ค่า VerifierConfig ) VerifierConfig specifying the verifiers to be run after every optimizer. |
| RewriterConfig.Builder | |
| RewriterConfig.Builder | setLayoutOptimizerValue (ค่า int) Optimize tensor layouts (default is ON) e.g. |
| RewriterConfig.Builder | |
| RewriterConfig.Builder | setLoopOptimizationValue (ค่า int) Loop optimizations (default is ON). |
| RewriterConfig.Builder | setMemoryOptimization (ค่า RewriterConfig.MemOptType ) Configures memory optimization passes through the meta-optimizer. |
| RewriterConfig.Builder | setMemoryOptimizationValue (ค่า int) Configures memory optimization passes through the meta-optimizer. |
| RewriterConfig.Builder | setMemoryOptimizerTargetNodeNameScope (ค่าสตริง) A node name scope for node names which are valid outputs of recomputations. |
| RewriterConfig.Builder | setMemoryOptimizerTargetNodeNameScopeBytes (ค่า com.google.protobuf.ByteString) A node name scope for node names which are valid outputs of recomputations. |
| RewriterConfig.Builder | setMetaOptimizerIterations (ค่า RewriterConfig.NumIterationsType ) Controls how many times we run the optimizers in meta optimizer (default is once). |
| RewriterConfig.Builder | setMetaOptimizerIterationsValue (ค่า int) Controls how many times we run the optimizers in meta optimizer (default is once). |
| RewriterConfig.Builder | setMetaOptimizerTimeoutMs (ค่ายาว) Maximum number of milliseconds to spend optimizing a single graph before timing out. |
| RewriterConfig.Builder | setMinGraphNodes (ค่า int) The minimum number of nodes in a graph to optimizer. |
| RewriterConfig.Builder | setOptimizers (ดัชนี int, ค่าสตริง) If non-empty, will use this as an alternative way to specify a list of optimizations to turn on and the order of the optimizations (replacing the meta-optimizer). |
| RewriterConfig.Builder | setPinToHostOptimization (ค่า RewriterConfig.Toggle ) Force small ops onto the CPU (default is OFF). |
| RewriterConfig.Builder | setPinToHostOptimizationValue (ค่า int) Force small ops onto the CPU (default is OFF). |
| RewriterConfig.Builder | setPostOptimizationVerifierConfig (ค่า VerifierConfig ) VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run. |
| RewriterConfig.Builder | setPostOptimizationVerifierConfig ( VerifierConfig.Builder builderForValue) VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run. |
| RewriterConfig.Builder | setRemapping (ค่า RewriterConfig.Toggle ) Remapping (default is ON) Remap subgraphs onto more efficient implementations. |
| RewriterConfig.Builder | setRemappingValue (ค่า int) Remapping (default is ON) Remap subgraphs onto more efficient implementations. |
| RewriterConfig.Builder | setRepeatedField (ฟิลด์ com.google.protobuf.Descriptors.FieldDescriptor, ดัชนี int, ค่าอ็อบเจ็กต์) |
| RewriterConfig.Builder | setScopedAllocatorOptimization (ค่า RewriterConfig.Toggle ) Try to allocate some independent Op outputs contiguously in order to merge or eliminate downstream Ops (off by default). |
| RewriterConfig.Builder | setScopedAllocatorOptimizationValue (ค่า int) Try to allocate some independent Op outputs contiguously in order to merge or eliminate downstream Ops (off by default). |
| RewriterConfig.Builder | setScopedAllocatorOpts (ค่า ScopedAllocatorOptions ) .tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16; |
| RewriterConfig.Builder | setScopedAllocatorOpts ( ScopedAllocatorOptions.Builder builderForValue) .tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16; |
| RewriterConfig.Builder | setShapeOptimization (ค่า RewriterConfig.Toggle ) Shape optimizations (default is ON) Simplify computations made on shapes. |
| RewriterConfig.Builder | setShapeOptimizationValue (ค่า int) Shape optimizations (default is ON) Simplify computations made on shapes. |
| RewriterConfig.Builder สุดท้าย | setUnknownFields (com.google.protobuf.UnknownFieldSetknownFields) |
วิธีการสืบทอด
วิธีการสาธารณะ
RewriterConfig.Builder สาธารณะ addAllCustomOptimizers (Iterable <? ขยาย RewriterConfig.CustomGraphOptimizer > ค่า)
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; RewriterConfig.Builder สาธารณะ addAllOptimizers (ค่า Iterable <String>)
If non-empty, will use this as an alternative way to specify a list of
optimizations to turn on and the order of the optimizations (replacing the
meta-optimizer).
Of the RewriterConfig options, only the AutoParallel configuration options
(the auto_parallel field) apply to manually requested optimization passes
("autoparallel"). Memory optimization passes ("memory") invoked here are
not configurable (in contrast to memory optimization passes through the
meta-optimizer) and act only on manual op annotations.
Custom optimizers (see custom_optimizers) that are not part of this
schedule will be run after - in the order that they were specified.
repeated string optimizers = 100; RewriterConfig.Builder สาธารณะ addCustomOptimizers ( RewriterConfig.CustomGraphOptimizer.Builder builderForValue)
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; RewriterConfig.Builder สาธารณะ addCustomOptimizers (ดัชนี int, RewriterConfig.CustomGraphOptimizer.Builder builderForValue)
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; RewriterConfig.Builder สาธารณะ addCustomOptimizers (ค่า RewriterConfig.CustomGraphOptimizer )
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; RewriterConfig.Builder สาธารณะ addCustomOptimizers (ดัชนี int, ค่า RewriterConfig.CustomGraphOptimizer )
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; RewriterConfig.CustomGraphOptimizer.Builder สาธารณะ addCustomOptimizersBuilder (ดัชนี int)
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; RewriterConfig.CustomGraphOptimizer.Builder สาธารณะ addCustomOptimizersBuilder ()
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; RewriterConfig.Builder addOptimizers สาธารณะ (ค่าสตริง)
If non-empty, will use this as an alternative way to specify a list of
optimizations to turn on and the order of the optimizations (replacing the
meta-optimizer).
Of the RewriterConfig options, only the AutoParallel configuration options
(the auto_parallel field) apply to manually requested optimization passes
("autoparallel"). Memory optimization passes ("memory") invoked here are
not configurable (in contrast to memory optimization passes through the
meta-optimizer) and act only on manual op annotations.
Custom optimizers (see custom_optimizers) that are not part of this
schedule will be run after - in the order that they were specified.
repeated string optimizers = 100; RewriterConfig.Builder สาธารณะ addOptimizersBytes (ค่า com.google.protobuf.ByteString)
If non-empty, will use this as an alternative way to specify a list of
optimizations to turn on and the order of the optimizations (replacing the
meta-optimizer).
Of the RewriterConfig options, only the AutoParallel configuration options
(the auto_parallel field) apply to manually requested optimization passes
("autoparallel"). Memory optimization passes ("memory") invoked here are
not configurable (in contrast to memory optimization passes through the
meta-optimizer) and act only on manual op annotations.
Custom optimizers (see custom_optimizers) that are not part of this
schedule will be run after - in the order that they were specified.
repeated string optimizers = 100; RewriterConfig.Builder สาธารณะ addRepeatedField (ฟิลด์ com.google.protobuf.Descriptors.FieldDescriptor ค่าอ็อบเจ็กต์)
RewriterConfig.Builder สาธารณะ clearArithmeticOptimization ()
Arithmetic optimizations (default is ON) e.g. Simplify arithmetic ops; merge ops with same value (like constants).
.tensorflow.RewriterConfig.Toggle arithmetic_optimization = 7; RewriterConfig.Builder สาธารณะ clearAutoMixedPrecision ()
Optimize data types for CUDA (default is OFF). This will try to use float16 on GPU which is faster. Note that this can change the numerical stability of the graph and may require the use of loss scaling to maintain model convergence.
.tensorflow.RewriterConfig.Toggle auto_mixed_precision = 23; RewriterConfig.Builder สาธารณะ clearAutoMixedPrecisionMkl ()
Optimize data types for MKL (default is OFF). This will try to use bfloat16 on CPUs, which is faster. Note that this can change the numerical stability of the graph.
.tensorflow.RewriterConfig.Toggle auto_mixed_precision_mkl = 25; RewriterConfig.Builder สาธารณะ clearAutoParallel ()
Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field.
.tensorflow.AutoParallelOptions auto_parallel = 5; RewriterConfig.Builder สาธารณะ clearCommonSubgraphElimination ()
Common subgraph elimination (default is ON) e.g. Simplify arithmetic ops; merge ops with same value (like constants).
.tensorflow.RewriterConfig.Toggle common_subgraph_elimination = 24; RewriterConfig.Builder สาธารณะ clearConstantFolding ()
Fold constants (default is ON) Statically infer the value of tensors when possible, and materialize the result using constants.
.tensorflow.RewriterConfig.Toggle constant_folding = 3; RewriterConfig.Builder สาธารณะ clearCpuLayoutConversion ()
CPU Conversion settings between NHCW and NCHW.
.tensorflow.RewriterConfig.CpuLayout cpu_layout_conversion = 50; RewriterConfig.Builder สาธารณะ clearCustomOptimizers ()
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; RewriterConfig.Builder สาธารณะ clearDebugStripper ()
Strips debug-related nodes from the graph (off by default).
.tensorflow.RewriterConfig.Toggle debug_stripper = 11; RewriterConfig.Builder สาธารณะ clearDependencyOptimization ()
Control dependency optimizations (default is ON). Remove redundant control dependencies, which may enable other optimization.
.tensorflow.RewriterConfig.Toggle dependency_optimization = 8; RewriterConfig.Builder สาธารณะ clearDisableMetaOptimizer ()
Disable the entire meta optimizer (off by default).
bool disable_meta_optimizer = 19; RewriterConfig.Builder สาธารณะ clearDisableModelPruning ()
If true, don't remove unnecessary ops from the graph
bool disable_model_pruning = 2; RewriterConfig.Builder สาธารณะ clearExperimentalDisableCompressedTensorOptimization ()
Disable optimizations that assume compressed tensors. Note that this flag is experimental and may be removed in the future.
bool experimental_disable_compressed_tensor_optimization = 26; RewriterConfig.Builder สาธารณะ clearFailOnOptimizerErrors ()
If true, any optimization pass failing will cause the MetaOptimizer to stop with an error. By default - or when set to false, failing passes are skipped silently.
bool fail_on_optimizer_errors = 21; RewriterConfig.Builder สาธารณะ clearFunctionOptimization ()
Function optimizations (default is ON).
.tensorflow.RewriterConfig.Toggle function_optimization = 10; RewriterConfig.Builder สาธารณะ clearImplementationSelector ()
Enable the swap of kernel implementations based on the device placement (default is ON).
.tensorflow.RewriterConfig.Toggle implementation_selector = 22; RewriterConfig.Builder สาธารณะ clearInterOptimizerVerifierConfig ()
VerifierConfig specifying the verifiers to be run after every optimizer.
.tensorflow.VerifierConfig inter_optimizer_verifier_config = 300; RewriterConfig.Builder สาธารณะ clearLayoutOptimizer ()
Optimize tensor layouts (default is ON) e.g. This will try to use NCHW layout on GPU which is faster.
.tensorflow.RewriterConfig.Toggle layout_optimizer = 1; RewriterConfig.Builder สาธารณะ clearLoopOptimization ()
Loop optimizations (default is ON).
.tensorflow.RewriterConfig.Toggle loop_optimization = 9; RewriterConfig.Builder สาธารณะ clearMemoryOptimization ()
Configures memory optimization passes through the meta-optimizer. Has no effect on manually requested memory optimization passes in the optimizers field.
.tensorflow.RewriterConfig.MemOptType memory_optimization = 4; RewriterConfig.Builder สาธารณะ clearMemoryOptimizerTargetNodeNameScope ()
A node name scope for node names which are valid outputs of recomputations. Inputs to nodes that match this scope may be recomputed (subject either to manual annotation of those input nodes or to manual annotation and heuristics depending on memory_optimization), but the nodes themselves will not be recomputed. This matches any sub-scopes as well, meaning the scope can appear not just as a top-level scope. For example, if the value is "gradients/", the default, it will match node name "gradients/foo", "foo/gradients/bar", but not "foo_gradients/"
string memory_optimizer_target_node_name_scope = 6; RewriterConfig.Builder สาธารณะ clearMetaOptimizerIterations ()
Controls how many times we run the optimizers in meta optimizer (default is once).
.tensorflow.RewriterConfig.NumIterationsType meta_optimizer_iterations = 12; RewriterConfig.Builder สาธารณะ clearMetaOptimizerTimeoutMs ()
Maximum number of milliseconds to spend optimizing a single graph before timing out. If equal to 0 the system picks a default (currently 5 minutes). If less than 0 the optimizer will never time out.
int64 meta_optimizer_timeout_ms = 20; RewriterConfig.Builder สาธารณะ clearMinGraphNodes ()
The minimum number of nodes in a graph to optimizer. For smaller graphs, optimization is skipped. 0 means the system picks an appropriate number. < 0 means do not skip optimization.
int32 min_graph_nodes = 17; RewriterConfig.Builder สาธารณะ clearOptimizers ()
If non-empty, will use this as an alternative way to specify a list of
optimizations to turn on and the order of the optimizations (replacing the
meta-optimizer).
Of the RewriterConfig options, only the AutoParallel configuration options
(the auto_parallel field) apply to manually requested optimization passes
("autoparallel"). Memory optimization passes ("memory") invoked here are
not configurable (in contrast to memory optimization passes through the
meta-optimizer) and act only on manual op annotations.
Custom optimizers (see custom_optimizers) that are not part of this
schedule will be run after - in the order that they were specified.
repeated string optimizers = 100; RewriterConfig.Builder สาธารณะ clearPinToHostOptimization ()
Force small ops onto the CPU (default is OFF).
.tensorflow.RewriterConfig.Toggle pin_to_host_optimization = 18; RewriterConfig.Builder สาธารณะ clearPostOptimizationVerifierConfig ()
VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run.
.tensorflow.VerifierConfig post_optimization_verifier_config = 301; RewriterConfig.Builder สาธารณะ clearRemapping ()
Remapping (default is ON) Remap subgraphs onto more efficient implementations.
.tensorflow.RewriterConfig.Toggle remapping = 14; RewriterConfig.Builder สาธารณะ clearScopedAllocatorOptimization ()
Try to allocate some independent Op outputs contiguously in order to merge or eliminate downstream Ops (off by default).
.tensorflow.RewriterConfig.Toggle scoped_allocator_optimization = 15; RewriterConfig.Builder สาธารณะ clearScopedAllocatorOpts ()
.tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16;
RewriterConfig.Builder สาธารณะ clearShapeOptimization ()
Shape optimizations (default is ON) Simplify computations made on shapes.
.tensorflow.RewriterConfig.Toggle shape_optimization = 13; สาธารณะ RewriterConfig.Toggle getArithmeticOptimization ()
Arithmetic optimizations (default is ON) e.g. Simplify arithmetic ops; merge ops with same value (like constants).
.tensorflow.RewriterConfig.Toggle arithmetic_optimization = 7; int สาธารณะ getArithmeticOptimizationValue ()
Arithmetic optimizations (default is ON) e.g. Simplify arithmetic ops; merge ops with same value (like constants).
.tensorflow.RewriterConfig.Toggle arithmetic_optimization = 7; RewriterConfig.Toggle สาธารณะ getAutoMixedPrecision ()
Optimize data types for CUDA (default is OFF). This will try to use float16 on GPU which is faster. Note that this can change the numerical stability of the graph and may require the use of loss scaling to maintain model convergence.
.tensorflow.RewriterConfig.Toggle auto_mixed_precision = 23; สาธารณะ RewriterConfig.Toggle getAutoMixedPrecisionMkl ()
Optimize data types for MKL (default is OFF). This will try to use bfloat16 on CPUs, which is faster. Note that this can change the numerical stability of the graph.
.tensorflow.RewriterConfig.Toggle auto_mixed_precision_mkl = 25; int สาธารณะ getAutoMixedPrecisionMklValue ()
Optimize data types for MKL (default is OFF). This will try to use bfloat16 on CPUs, which is faster. Note that this can change the numerical stability of the graph.
.tensorflow.RewriterConfig.Toggle auto_mixed_precision_mkl = 25; int สาธารณะ getAutoMixedPrecisionValue ()
Optimize data types for CUDA (default is OFF). This will try to use float16 on GPU which is faster. Note that this can change the numerical stability of the graph and may require the use of loss scaling to maintain model convergence.
.tensorflow.RewriterConfig.Toggle auto_mixed_precision = 23; AutoParallelOptions สาธารณะ getAutoParallel ()
Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field.
.tensorflow.AutoParallelOptions auto_parallel = 5; AutoParallelOptions.Builder สาธารณะ getAutoParallelBuilder ()
Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field.
.tensorflow.AutoParallelOptions auto_parallel = 5; AutoParallelOptionsOrBuilder สาธารณะ รับ AutoParallelOrBuilder ()
Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field.
.tensorflow.AutoParallelOptions auto_parallel = 5; RewriterConfig สาธารณะ สลับ getCommonSubgraphElimination ()
Common subgraph elimination (default is ON) e.g. Simplify arithmetic ops; merge ops with same value (like constants).
.tensorflow.RewriterConfig.Toggle common_subgraph_elimination = 24; int สาธารณะ getCommonSubgraphEliminationValue ()
Common subgraph elimination (default is ON) e.g. Simplify arithmetic ops; merge ops with same value (like constants).
.tensorflow.RewriterConfig.Toggle common_subgraph_elimination = 24; RewriterConfig.Toggle สาธารณะ getConstantFolding ()
Fold constants (default is ON) Statically infer the value of tensors when possible, and materialize the result using constants.
.tensorflow.RewriterConfig.Toggle constant_folding = 3; int สาธารณะ getConstantFoldingValue ()
Fold constants (default is ON) Statically infer the value of tensors when possible, and materialize the result using constants.
.tensorflow.RewriterConfig.Toggle constant_folding = 3; RewriterConfig.CpuLayout สาธารณะ getCpuLayoutConversion ()
CPU Conversion settings between NHCW and NCHW.
.tensorflow.RewriterConfig.CpuLayout cpu_layout_conversion = 50; int สาธารณะ getCpuLayoutConversionValue ()
CPU Conversion settings between NHCW and NCHW.
.tensorflow.RewriterConfig.CpuLayout cpu_layout_conversion = 50; RewriterConfig.CustomGraphOptimizer สาธารณะ getCustomOptimizers (ดัชนี int)
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; RewriterConfig.CustomGraphOptimizer.Builder สาธารณะ getCustomOptimizersBuilder (ดัชนี int)
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; รายการสาธารณะ < RewriterConfig.CustomGraphOptimizer.Builder > getCustomOptimizersBuilderList ()
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; int สาธารณะ getCustomOptimizersCount ()
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; รายการสาธารณะ < RewriterConfig.CustomGraphOptimizer > getCustomOptimizersList ()
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; RewriterConfig.CustomGraphOptimizerOrBuilder สาธารณะ getCustomOptimizersOrBuilder (ดัชนี int)
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; รายการสาธารณะ<? ขยาย RewriterConfig.CustomGraphOptimizerOrBuilder > getCustomOptimizersOrBuilderList ()
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; RewriterConfig.Toggle สาธารณะ getDebugStripper ()
Strips debug-related nodes from the graph (off by default).
.tensorflow.RewriterConfig.Toggle debug_stripper = 11; int สาธารณะ getDebugStripperValue ()
Strips debug-related nodes from the graph (off by default).
.tensorflow.RewriterConfig.Toggle debug_stripper = 11; RewriterConfig.Toggle สาธารณะ getDependencyOptimization ()
Control dependency optimizations (default is ON). Remove redundant control dependencies, which may enable other optimization.
.tensorflow.RewriterConfig.Toggle dependency_optimization = 8; สาธารณะ int getDependencyOptimizationValue ()
Control dependency optimizations (default is ON). Remove redundant control dependencies, which may enable other optimization.
.tensorflow.RewriterConfig.Toggle dependency_optimization = 8; สาธารณะคงที่สุดท้าย com.google.protobuf.Descriptors.Descriptor getDescriptor ()
สาธารณะ com.google.protobuf.Descriptors.Descriptor getDescriptorForType ()
บูลีนสาธารณะ getDisableMetaOptimizer ()
Disable the entire meta optimizer (off by default).
bool disable_meta_optimizer = 19; บูลีนสาธารณะ getDisableModelPruning ()
If true, don't remove unnecessary ops from the graph
bool disable_model_pruning = 2; บูลีนสาธารณะ getExperimentalDisableCompressedTensorOptimization ()
Disable optimizations that assume compressed tensors. Note that this flag is experimental and may be removed in the future.
bool experimental_disable_compressed_tensor_optimization = 26; บูลีนสาธารณะ getFailOnOptimizerErrors ()
If true, any optimization pass failing will cause the MetaOptimizer to stop with an error. By default - or when set to false, failing passes are skipped silently.
bool fail_on_optimizer_errors = 21; RewriterConfig.Toggle สาธารณะ getFunctionOptimization ()
Function optimizations (default is ON).
.tensorflow.RewriterConfig.Toggle function_optimization = 10; สาธารณะ int getFunctionOptimizationValue ()
Function optimizations (default is ON).
.tensorflow.RewriterConfig.Toggle function_optimization = 10; RewriterConfig.Toggle getImplementationSelector สาธารณะ ()
Enable the swap of kernel implementations based on the device placement (default is ON).
.tensorflow.RewriterConfig.Toggle implementation_selector = 22; สาธารณะ int getImplementationSelectorValue ()
Enable the swap of kernel implementations based on the device placement (default is ON).
.tensorflow.RewriterConfig.Toggle implementation_selector = 22; VerifierConfig สาธารณะ getInterOptimizerVerifierConfig ()
VerifierConfig specifying the verifiers to be run after every optimizer.
.tensorflow.VerifierConfig inter_optimizer_verifier_config = 300; VerifierConfig.Builder สาธารณะ getInterOptimizerVerifierConfigBuilder ()
VerifierConfig specifying the verifiers to be run after every optimizer.
.tensorflow.VerifierConfig inter_optimizer_verifier_config = 300; VerifierConfigOrBuilder สาธารณะ getInterOptimizerVerifierConfigOrBuilder ()
VerifierConfig specifying the verifiers to be run after every optimizer.
.tensorflow.VerifierConfig inter_optimizer_verifier_config = 300; RewriterConfig.Toggle getLayoutOptimizer สาธารณะ ()
Optimize tensor layouts (default is ON) e.g. This will try to use NCHW layout on GPU which is faster.
.tensorflow.RewriterConfig.Toggle layout_optimizer = 1; สาธารณะ int getLayoutOptimizerValue ()
Optimize tensor layouts (default is ON) e.g. This will try to use NCHW layout on GPU which is faster.
.tensorflow.RewriterConfig.Toggle layout_optimizer = 1; สาธารณะ RewriterConfig.Toggle getLoopOptimization ()
Loop optimizations (default is ON).
.tensorflow.RewriterConfig.Toggle loop_optimization = 9; สาธารณะ int getLoopOptimizationValue ()
Loop optimizations (default is ON).
.tensorflow.RewriterConfig.Toggle loop_optimization = 9; RewriterConfig.MemOptType สาธารณะ getMemoryOptimization ()
Configures memory optimization passes through the meta-optimizer. Has no effect on manually requested memory optimization passes in the optimizers field.
.tensorflow.RewriterConfig.MemOptType memory_optimization = 4; int สาธารณะ getMemoryOptimizationValue ()
Configures memory optimization passes through the meta-optimizer. Has no effect on manually requested memory optimization passes in the optimizers field.
.tensorflow.RewriterConfig.MemOptType memory_optimization = 4; สตริงสาธารณะ getMemoryOptimizerTargetNodeNameScope ()
A node name scope for node names which are valid outputs of recomputations. Inputs to nodes that match this scope may be recomputed (subject either to manual annotation of those input nodes or to manual annotation and heuristics depending on memory_optimization), but the nodes themselves will not be recomputed. This matches any sub-scopes as well, meaning the scope can appear not just as a top-level scope. For example, if the value is "gradients/", the default, it will match node name "gradients/foo", "foo/gradients/bar", but not "foo_gradients/"
string memory_optimizer_target_node_name_scope = 6; สาธารณะ com.google.protobuf.ByteString getMemoryOptimizerTargetNodeNameScopeBytes ()
A node name scope for node names which are valid outputs of recomputations. Inputs to nodes that match this scope may be recomputed (subject either to manual annotation of those input nodes or to manual annotation and heuristics depending on memory_optimization), but the nodes themselves will not be recomputed. This matches any sub-scopes as well, meaning the scope can appear not just as a top-level scope. For example, if the value is "gradients/", the default, it will match node name "gradients/foo", "foo/gradients/bar", but not "foo_gradients/"
string memory_optimizer_target_node_name_scope = 6; RewriterConfig.NumIterationsType สาธารณะ getMetaOptimizerIterations ()
Controls how many times we run the optimizers in meta optimizer (default is once).
.tensorflow.RewriterConfig.NumIterationsType meta_optimizer_iterations = 12; int สาธารณะ getMetaOptimizerIterationsValue ()
Controls how many times we run the optimizers in meta optimizer (default is once).
.tensorflow.RewriterConfig.NumIterationsType meta_optimizer_iterations = 12; สาธารณะยาว getMetaOptimizerTimeoutMs ()
Maximum number of milliseconds to spend optimizing a single graph before timing out. If equal to 0 the system picks a default (currently 5 minutes). If less than 0 the optimizer will never time out.
int64 meta_optimizer_timeout_ms = 20; สาธารณะ int getMinGraphNodes ()
The minimum number of nodes in a graph to optimizer. For smaller graphs, optimization is skipped. 0 means the system picks an appropriate number. < 0 means do not skip optimization.
int32 min_graph_nodes = 17; สตริงสาธารณะ getOptimizers (ดัชนี int)
If non-empty, will use this as an alternative way to specify a list of
optimizations to turn on and the order of the optimizations (replacing the
meta-optimizer).
Of the RewriterConfig options, only the AutoParallel configuration options
(the auto_parallel field) apply to manually requested optimization passes
("autoparallel"). Memory optimization passes ("memory") invoked here are
not configurable (in contrast to memory optimization passes through the
meta-optimizer) and act only on manual op annotations.
Custom optimizers (see custom_optimizers) that are not part of this
schedule will be run after - in the order that they were specified.
repeated string optimizers = 100; สาธารณะ com.google.protobuf.ByteString getOptimizersBytes (ดัชนี int)
If non-empty, will use this as an alternative way to specify a list of
optimizations to turn on and the order of the optimizations (replacing the
meta-optimizer).
Of the RewriterConfig options, only the AutoParallel configuration options
(the auto_parallel field) apply to manually requested optimization passes
("autoparallel"). Memory optimization passes ("memory") invoked here are
not configurable (in contrast to memory optimization passes through the
meta-optimizer) and act only on manual op annotations.
Custom optimizers (see custom_optimizers) that are not part of this
schedule will be run after - in the order that they were specified.
repeated string optimizers = 100; สาธารณะ int getOptimizersCount ()
If non-empty, will use this as an alternative way to specify a list of
optimizations to turn on and the order of the optimizations (replacing the
meta-optimizer).
Of the RewriterConfig options, only the AutoParallel configuration options
(the auto_parallel field) apply to manually requested optimization passes
("autoparallel"). Memory optimization passes ("memory") invoked here are
not configurable (in contrast to memory optimization passes through the
meta-optimizer) and act only on manual op annotations.
Custom optimizers (see custom_optimizers) that are not part of this
schedule will be run after - in the order that they were specified.
repeated string optimizers = 100; สาธารณะ com.google.protobuf.ProtocolStringList getOptimizersList ()
If non-empty, will use this as an alternative way to specify a list of
optimizations to turn on and the order of the optimizations (replacing the
meta-optimizer).
Of the RewriterConfig options, only the AutoParallel configuration options
(the auto_parallel field) apply to manually requested optimization passes
("autoparallel"). Memory optimization passes ("memory") invoked here are
not configurable (in contrast to memory optimization passes through the
meta-optimizer) and act only on manual op annotations.
Custom optimizers (see custom_optimizers) that are not part of this
schedule will be run after - in the order that they were specified.
repeated string optimizers = 100; RewriterConfig สาธารณะ สลับ getPinToHostOptimization ()
Force small ops onto the CPU (default is OFF).
.tensorflow.RewriterConfig.Toggle pin_to_host_optimization = 18; int สาธารณะ getPinToHostOptimizationValue ()
Force small ops onto the CPU (default is OFF).
.tensorflow.RewriterConfig.Toggle pin_to_host_optimization = 18; VerifierConfig สาธารณะ getPostOptimizationVerifierConfig ()
VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run.
.tensorflow.VerifierConfig post_optimization_verifier_config = 301; VerifierConfig.Builder สาธารณะ getPostOptimizationVerifierConfigBuilder ()
VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run.
.tensorflow.VerifierConfig post_optimization_verifier_config = 301; VerifierConfigOrBuilder สาธารณะ getPostOptimizationVerifierConfigOrBuilder ()
VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run.
.tensorflow.VerifierConfig post_optimization_verifier_config = 301; RewriterConfig.Toggle สาธารณะ getRemapping ()
Remapping (default is ON) Remap subgraphs onto more efficient implementations.
.tensorflow.RewriterConfig.Toggle remapping = 14; สาธารณะ int getRemappingValue ()
Remapping (default is ON) Remap subgraphs onto more efficient implementations.
.tensorflow.RewriterConfig.Toggle remapping = 14; RewriterConfig.Toggle สาธารณะ getScopedAllocatorOptimization ()
Try to allocate some independent Op outputs contiguously in order to merge or eliminate downstream Ops (off by default).
.tensorflow.RewriterConfig.Toggle scoped_allocator_optimization = 15; int สาธารณะ getScopedAllocatorOptimizationValue ()
Try to allocate some independent Op outputs contiguously in order to merge or eliminate downstream Ops (off by default).
.tensorflow.RewriterConfig.Toggle scoped_allocator_optimization = 15; สาธารณะ ScopedAllocatorOptions getScopedAllocatorOpts ()
.tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16;
สาธารณะ ScopedAllocatorOptions.Builder getScopedAllocatorOptsBuilder ()
.tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16;
สาธารณะ ScopedAllocatorOptionsOrBuilder getScopedAllocatorOptsOrBuilder ()
.tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16;
RewriterConfig.Toggle สาธารณะ getShapeOptimization ()
Shape optimizations (default is ON) Simplify computations made on shapes.
.tensorflow.RewriterConfig.Toggle shape_optimization = 13; int สาธารณะ getShapeOptimizationValue ()
Shape optimizations (default is ON) Simplify computations made on shapes.
.tensorflow.RewriterConfig.Toggle shape_optimization = 13; บูลีนสาธารณะ hasAutoParallel ()
Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field.
.tensorflow.AutoParallelOptions auto_parallel = 5; บูลีนสาธารณะ hasInterOptimizerVerifierConfig ()
VerifierConfig specifying the verifiers to be run after every optimizer.
.tensorflow.VerifierConfig inter_optimizer_verifier_config = 300; บูลีนสาธารณะ hasPostOptimizationVerifierConfig ()
VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run.
.tensorflow.VerifierConfig post_optimization_verifier_config = 301; บูลีนสาธารณะ hasScopedAllocatorOpts ()
.tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16;
บูลีนสุดท้ายสาธารณะ isInitialized ()
RewriterConfig.Builder สาธารณะ ผสาน AutoParallel (ค่า AutoParallelOptions )
Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field.
.tensorflow.AutoParallelOptions auto_parallel = 5; RewriterConfig.Builder สาธารณะ ผสานจาก (com.google.protobuf.CodedInputStream อินพุต com.google.protobuf.ExtensionRegistryLite extensionRegistry)
ขว้าง
| IOข้อยกเว้น |
|---|
RewriterConfig.Builder สาธารณะ ผสาน InterOptimizerVerifierConfig (ค่า VerifierConfig )
VerifierConfig specifying the verifiers to be run after every optimizer.
.tensorflow.VerifierConfig inter_optimizer_verifier_config = 300; สาธารณะ RewriterConfig.Builder ผสาน PostOptimizationVerifierConfig (ค่า VerifierConfig )
VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run.
.tensorflow.VerifierConfig post_optimization_verifier_config = 301; RewriterConfig.Builder สาธารณะ ผสาน ScopedAllocatorOpts (ค่า ScopedAllocatorOptions )
.tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16;
RewriterConfig.Builder สาธารณะขั้นสุดท้าย ผสาน UnknownFields (com.google.protobuf.UnknownFieldSetknownFields)
RewriterConfig.Builder สาธารณะ RemoveCustomOptimizers (ดัชนี int)
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; RewriterConfig.Builder สาธารณะ setArithmeticOptimization (ค่า RewriterConfig.Toggle )
Arithmetic optimizations (default is ON) e.g. Simplify arithmetic ops; merge ops with same value (like constants).
.tensorflow.RewriterConfig.Toggle arithmetic_optimization = 7; RewriterConfig.Builder สาธารณะ setArithmeticOptimizationValue (ค่า int)
Arithmetic optimizations (default is ON) e.g. Simplify arithmetic ops; merge ops with same value (like constants).
.tensorflow.RewriterConfig.Toggle arithmetic_optimization = 7; RewriterConfig.Builder สาธารณะ setAutoMixedPrecision (ค่า RewriterConfig.Toggle )
Optimize data types for CUDA (default is OFF). This will try to use float16 on GPU which is faster. Note that this can change the numerical stability of the graph and may require the use of loss scaling to maintain model convergence.
.tensorflow.RewriterConfig.Toggle auto_mixed_precision = 23; RewriterConfig.Builder สาธารณะ ตั้งค่า AutoMixedPrecisionMkl (ค่า RewriterConfig.Toggle )
Optimize data types for MKL (default is OFF). This will try to use bfloat16 on CPUs, which is faster. Note that this can change the numerical stability of the graph.
.tensorflow.RewriterConfig.Toggle auto_mixed_precision_mkl = 25; RewriterConfig.Builder สาธารณะ ตั้งค่า AutoMixedPrecisionMklValue (ค่า int)
Optimize data types for MKL (default is OFF). This will try to use bfloat16 on CPUs, which is faster. Note that this can change the numerical stability of the graph.
.tensorflow.RewriterConfig.Toggle auto_mixed_precision_mkl = 25; RewriterConfig.Builder สาธารณะ ตั้งค่า AutoMixedPrecisionValue (ค่า int)
Optimize data types for CUDA (default is OFF). This will try to use float16 on GPU which is faster. Note that this can change the numerical stability of the graph and may require the use of loss scaling to maintain model convergence.
.tensorflow.RewriterConfig.Toggle auto_mixed_precision = 23; RewriterConfig.Builder สาธารณะ setAutoParallel ( AutoParallelOptions.Builder builderForValue)
Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field.
.tensorflow.AutoParallelOptions auto_parallel = 5;RewriterConfig.Builder สาธารณะ setAutoParallel (ค่า AutoParallelOptions )
Configures AutoParallel optimization passes either through the meta-optimizer or when manually specified through the optimizers field.
.tensorflow.AutoParallelOptions auto_parallel = 5; RewriterConfig.Builder สาธารณะ setCommonSubgraphElimination (ค่า RewriterConfig.Toggle )
Common subgraph elimination (default is ON) e.g. Simplify arithmetic ops; merge ops with same value (like constants).
.tensorflow.RewriterConfig.Toggle common_subgraph_elimination = 24; RewriterConfig.Builder สาธารณะ setCommonSubgraphEliminationValue (ค่า int)
Common subgraph elimination (default is ON) e.g. Simplify arithmetic ops; merge ops with same value (like constants).
.tensorflow.RewriterConfig.Toggle common_subgraph_elimination = 24; RewriterConfig.Builder สาธารณะ setConstantFolding (ค่า RewriterConfig.Toggle )
Fold constants (default is ON) Statically infer the value of tensors when possible, and materialize the result using constants.
.tensorflow.RewriterConfig.Toggle constant_folding = 3; RewriterConfig.Builder สาธารณะ setConstantFoldingValue (ค่า int)
Fold constants (default is ON) Statically infer the value of tensors when possible, and materialize the result using constants.
.tensorflow.RewriterConfig.Toggle constant_folding = 3; RewriterConfig.Builder สาธารณะ setCpuLayoutConversion (ค่า RewriterConfig.CpuLayout )
CPU Conversion settings between NHCW and NCHW.
.tensorflow.RewriterConfig.CpuLayout cpu_layout_conversion = 50; RewriterConfig.Builder สาธารณะ setCpuLayoutConversionValue (ค่า int)
CPU Conversion settings between NHCW and NCHW.
.tensorflow.RewriterConfig.CpuLayout cpu_layout_conversion = 50; RewriterConfig.Builder สาธารณะ setCustomOptimizers (ดัชนี int, RewriterConfig.CustomGraphOptimizer.Builder builderForValue)
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; RewriterConfig.Builder สาธารณะ setCustomOptimizers (ดัชนี int, ค่า RewriterConfig.CustomGraphOptimizer )
list of CustomGraphOptimizers to apply.
repeated .tensorflow.RewriterConfig.CustomGraphOptimizer custom_optimizers = 200; RewriterConfig.Builder สาธารณะ setDebugStripper (ค่า RewriterConfig.Toggle )
Strips debug-related nodes from the graph (off by default).
.tensorflow.RewriterConfig.Toggle debug_stripper = 11; RewriterConfig.Builder สาธารณะ setDebugStripperValue (ค่า int)
Strips debug-related nodes from the graph (off by default).
.tensorflow.RewriterConfig.Toggle debug_stripper = 11; RewriterConfig.Builder สาธารณะ setDependencyOptimization (ค่า RewriterConfig.Toggle )
Control dependency optimizations (default is ON). Remove redundant control dependencies, which may enable other optimization.
.tensorflow.RewriterConfig.Toggle dependency_optimization = 8; RewriterConfig.Builder สาธารณะ setDependencyOptimizationValue (ค่า int)
Control dependency optimizations (default is ON). Remove redundant control dependencies, which may enable other optimization.
.tensorflow.RewriterConfig.Toggle dependency_optimization = 8; RewriterConfig.Builder สาธารณะ setDisableMetaOptimizer (ค่าบูลีน)
Disable the entire meta optimizer (off by default).
bool disable_meta_optimizer = 19; RewriterConfig.Builder สาธารณะ setDisableModelPruning (ค่าบูลีน)
If true, don't remove unnecessary ops from the graph
bool disable_model_pruning = 2; RewriterConfig.Builder สาธารณะ setExperimentalDisableCompressedTensorOptimization (ค่าบูลีน)
Disable optimizations that assume compressed tensors. Note that this flag is experimental and may be removed in the future.
bool experimental_disable_compressed_tensor_optimization = 26; RewriterConfig.Builder สาธารณะ setFailOnOptimizerErrors (ค่าบูลีน)
If true, any optimization pass failing will cause the MetaOptimizer to stop with an error. By default - or when set to false, failing passes are skipped silently.
bool fail_on_optimizer_errors = 21; RewriterConfig.Builder setField สาธารณะ (ฟิลด์ com.google.protobuf.Descriptors.FieldDescriptor ค่าอ็อบเจ็กต์)
RewriterConfig.Builder สาธารณะ setFunctionOptimization (ค่า RewriterConfig.Toggle )
Function optimizations (default is ON).
.tensorflow.RewriterConfig.Toggle function_optimization = 10; RewriterConfig.Builder สาธารณะ setFunctionOptimizationValue (ค่า int)
Function optimizations (default is ON).
.tensorflow.RewriterConfig.Toggle function_optimization = 10; RewriterConfig.Builder สาธารณะ setImplementationSelector (ค่า RewriterConfig.Toggle )
Enable the swap of kernel implementations based on the device placement (default is ON).
.tensorflow.RewriterConfig.Toggle implementation_selector = 22; RewriterConfig.Builder สาธารณะ setImplementationSelectorValue (ค่า int)
Enable the swap of kernel implementations based on the device placement (default is ON).
.tensorflow.RewriterConfig.Toggle implementation_selector = 22; RewriterConfig.Builder สาธารณะ setInterOptimizerVerifierConfig ( VerifierConfig.Builder builderForValue)
VerifierConfig specifying the verifiers to be run after every optimizer.
.tensorflow.VerifierConfig inter_optimizer_verifier_config = 300; RewriterConfig.Builder สาธารณะ setInterOptimizerVerifierConfig (ค่า VerifierConfig )
VerifierConfig specifying the verifiers to be run after every optimizer.
.tensorflow.VerifierConfig inter_optimizer_verifier_config = 300; RewriterConfig.Builder สาธารณะ setLayoutOptimizer (ค่า RewriterConfig.Toggle )
Optimize tensor layouts (default is ON) e.g. This will try to use NCHW layout on GPU which is faster.
.tensorflow.RewriterConfig.Toggle layout_optimizer = 1; RewriterConfig.Builder สาธารณะ setLayoutOptimizerValue (ค่า int)
Optimize tensor layouts (default is ON) e.g. This will try to use NCHW layout on GPU which is faster.
.tensorflow.RewriterConfig.Toggle layout_optimizer = 1; RewriterConfig.Builder สาธารณะ setLoopOptimization (ค่า RewriterConfig.Toggle )
Loop optimizations (default is ON).
.tensorflow.RewriterConfig.Toggle loop_optimization = 9; RewriterConfig.Builder สาธารณะ setLoopOptimizationValue (ค่า int)
Loop optimizations (default is ON).
.tensorflow.RewriterConfig.Toggle loop_optimization = 9; RewriterConfig.Builder สาธารณะ setMemoryOptimization (ค่า RewriterConfig.MemOptType )
Configures memory optimization passes through the meta-optimizer. Has no effect on manually requested memory optimization passes in the optimizers field.
.tensorflow.RewriterConfig.MemOptType memory_optimization = 4; RewriterConfig.Builder สาธารณะ setMemoryOptimizationValue (ค่า int)
Configures memory optimization passes through the meta-optimizer. Has no effect on manually requested memory optimization passes in the optimizers field.
.tensorflow.RewriterConfig.MemOptType memory_optimization = 4; RewriterConfig.Builder สาธารณะ setMemoryOptimizerTargetNodeNameScope (ค่าสตริง)
A node name scope for node names which are valid outputs of recomputations. Inputs to nodes that match this scope may be recomputed (subject either to manual annotation of those input nodes or to manual annotation and heuristics depending on memory_optimization), but the nodes themselves will not be recomputed. This matches any sub-scopes as well, meaning the scope can appear not just as a top-level scope. For example, if the value is "gradients/", the default, it will match node name "gradients/foo", "foo/gradients/bar", but not "foo_gradients/"
string memory_optimizer_target_node_name_scope = 6; RewriterConfig.Builder สาธารณะ setMemoryOptimizerTargetNodeNameScopeBytes (ค่า com.google.protobuf.ByteString)
A node name scope for node names which are valid outputs of recomputations. Inputs to nodes that match this scope may be recomputed (subject either to manual annotation of those input nodes or to manual annotation and heuristics depending on memory_optimization), but the nodes themselves will not be recomputed. This matches any sub-scopes as well, meaning the scope can appear not just as a top-level scope. For example, if the value is "gradients/", the default, it will match node name "gradients/foo", "foo/gradients/bar", but not "foo_gradients/"
string memory_optimizer_target_node_name_scope = 6; RewriterConfig.Builder สาธารณะ setMetaOptimizerIterations (ค่า RewriterConfig.NumIterationsType )
Controls how many times we run the optimizers in meta optimizer (default is once).
.tensorflow.RewriterConfig.NumIterationsType meta_optimizer_iterations = 12; RewriterConfig.Builder สาธารณะ setMetaOptimizerIterationsValue (ค่า int)
Controls how many times we run the optimizers in meta optimizer (default is once).
.tensorflow.RewriterConfig.NumIterationsType meta_optimizer_iterations = 12; RewriterConfig.Builder สาธารณะ setMetaOptimizerTimeoutMs (ค่ายาว)
Maximum number of milliseconds to spend optimizing a single graph before timing out. If equal to 0 the system picks a default (currently 5 minutes). If less than 0 the optimizer will never time out.
int64 meta_optimizer_timeout_ms = 20; RewriterConfig.Builder สาธารณะ setMinGraphNodes (ค่า int)
The minimum number of nodes in a graph to optimizer. For smaller graphs, optimization is skipped. 0 means the system picks an appropriate number. < 0 means do not skip optimization.
int32 min_graph_nodes = 17; RewriterConfig.Builder setOptimizers สาธารณะ (ดัชนี int, ค่าสตริง)
If non-empty, will use this as an alternative way to specify a list of
optimizations to turn on and the order of the optimizations (replacing the
meta-optimizer).
Of the RewriterConfig options, only the AutoParallel configuration options
(the auto_parallel field) apply to manually requested optimization passes
("autoparallel"). Memory optimization passes ("memory") invoked here are
not configurable (in contrast to memory optimization passes through the
meta-optimizer) and act only on manual op annotations.
Custom optimizers (see custom_optimizers) that are not part of this
schedule will be run after - in the order that they were specified.
repeated string optimizers = 100; RewriterConfig.Builder สาธารณะ setPinToHostOptimization (ค่า RewriterConfig.Toggle )
Force small ops onto the CPU (default is OFF).
.tensorflow.RewriterConfig.Toggle pin_to_host_optimization = 18; RewriterConfig.Builder สาธารณะ setPinToHostOptimizationValue (ค่า int)
Force small ops onto the CPU (default is OFF).
.tensorflow.RewriterConfig.Toggle pin_to_host_optimization = 18; RewriterConfig.Builder สาธารณะ setPostOptimizationVerifierConfig (ค่า VerifierConfig )
VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run.
.tensorflow.VerifierConfig post_optimization_verifier_config = 301; RewriterConfig.Builder สาธารณะ setPostOptimizationVerifierConfig ( VerifierConfig.Builder builderForValue)
VerifierConfig specifying the verifiers to be run at the end, after all optimizers have run.
.tensorflow.VerifierConfig post_optimization_verifier_config = 301; RewriterConfig.Builder สาธารณะ setRemapping (ค่า RewriterConfig.Toggle )
Remapping (default is ON) Remap subgraphs onto more efficient implementations.
.tensorflow.RewriterConfig.Toggle remapping = 14; RewriterConfig.Builder สาธารณะ setRemappingValue (ค่า int)
Remapping (default is ON) Remap subgraphs onto more efficient implementations.
.tensorflow.RewriterConfig.Toggle remapping = 14; RewriterConfig.Builder สาธารณะ setRepeatedField (ฟิลด์ com.google.protobuf.Descriptors.FieldDescriptor, ดัชนี int, ค่าอ็อบเจ็กต์)
RewriterConfig.Builder สาธารณะ setScopedAllocatorOptimization (ค่า RewriterConfig.Toggle )
Try to allocate some independent Op outputs contiguously in order to merge or eliminate downstream Ops (off by default).
.tensorflow.RewriterConfig.Toggle scoped_allocator_optimization = 15; RewriterConfig.Builder สาธารณะ setScopedAllocatorOptimizationValue (ค่า int)
Try to allocate some independent Op outputs contiguously in order to merge or eliminate downstream Ops (off by default).
.tensorflow.RewriterConfig.Toggle scoped_allocator_optimization = 15; RewriterConfig.Builder สาธารณะ setScopedAllocatorOpts (ค่า ScopedAllocatorOptions )
.tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16;
RewriterConfig.Builder สาธารณะ setScopedAllocatorOpts ( ScopedAllocatorOptions.Builder builderForValue)
.tensorflow.ScopedAllocatorOptions scoped_allocator_opts = 16;
RewriterConfig.Builder สาธารณะ setShapeOptimization (ค่า RewriterConfig.Toggle )
Shape optimizations (default is ON) Simplify computations made on shapes.
.tensorflow.RewriterConfig.Toggle shape_optimization = 13; RewriterConfig.Builder สาธารณะ setShapeOptimizationValue (ค่า int)
Shape optimizations (default is ON) Simplify computations made on shapes.
.tensorflow.RewriterConfig.Toggle shape_optimization = 13;