Package onnx
Interface Onnx.ModelProtoOrBuilder
- All Superinterfaces:
com.google.protobuf.MessageLiteOrBuilder
,com.google.protobuf.MessageOrBuilder
- All Known Implementing Classes:
Onnx.ModelProto
,Onnx.ModelProto.Builder
- Enclosing class:
- Onnx
public static interface Onnx.ModelProtoOrBuilder
extends com.google.protobuf.MessageOrBuilder
-
Method Summary
Modifier and TypeMethodDescriptionA human-readable documentation for this model.com.google.protobuf.ByteString
A human-readable documentation for this model.Domain name of the model.com.google.protobuf.ByteString
Domain name of the model.getFunctions
(int index) A list of function protos local to the model.int
A list of function protos local to the model.A list of function protos local to the model.getFunctionsOrBuilder
(int index) A list of function protos local to the model.List<? extends Onnx.FunctionProtoOrBuilder>
A list of function protos local to the model.getGraph()
The parameterized graph that is evaluated to execute the model.The parameterized graph that is evaluated to execute the model.long
The version of the IR this model targets.getMetadataProps
(int index) Named metadata values; keys should be distinct.int
Named metadata values; keys should be distinct.Named metadata values; keys should be distinct.getMetadataPropsOrBuilder
(int index) Named metadata values; keys should be distinct.List<? extends Onnx.StringStringEntryProtoOrBuilder>
Named metadata values; keys should be distinct.long
The version of the graph encoded.getOpsetImport
(int index) The OperatorSets this model relies on.int
The OperatorSets this model relies on.The OperatorSets this model relies on.getOpsetImportOrBuilder
(int index) The OperatorSets this model relies on.List<? extends Onnx.OperatorSetIdProtoOrBuilder>
The OperatorSets this model relies on.The name of the framework or tool used to generate this model.com.google.protobuf.ByteString
The name of the framework or tool used to generate this model.The version of the framework or tool used to generate this model.com.google.protobuf.ByteString
The version of the framework or tool used to generate this model.getTrainingInfo
(int index) Training-specific information.int
Training-specific information.Training-specific information.getTrainingInfoOrBuilder
(int index) Training-specific information.List<? extends Onnx.TrainingInfoProtoOrBuilder>
Training-specific information.boolean
A human-readable documentation for this model.boolean
Domain name of the model.boolean
hasGraph()
The parameterized graph that is evaluated to execute the model.boolean
The version of the IR this model targets.boolean
The version of the graph encoded.boolean
The name of the framework or tool used to generate this model.boolean
The version of the framework or tool used to generate this model.Methods inherited from interface com.google.protobuf.MessageLiteOrBuilder
isInitialized
Methods inherited from interface com.google.protobuf.MessageOrBuilder
findInitializationErrors, getAllFields, getDefaultInstanceForType, getDescriptorForType, getField, getInitializationErrorString, getOneofFieldDescriptor, getRepeatedField, getRepeatedFieldCount, getUnknownFields, hasField, hasOneof
-
Method Details
-
hasIrVersion
boolean hasIrVersion()The version of the IR this model targets. See Version enum above. This field MUST be present.
optional int64 ir_version = 1;
- Returns:
- Whether the irVersion field is set.
-
getIrVersion
long getIrVersion()The version of the IR this model targets. See Version enum above. This field MUST be present.
optional int64 ir_version = 1;
- Returns:
- The irVersion.
-
getOpsetImportList
List<Onnx.OperatorSetIdProto> getOpsetImportList()The OperatorSets this model relies on. All ModelProtos MUST have at least one entry that specifies which version of the ONNX OperatorSet is being imported. All nodes in the ModelProto's graph will bind against the operator with the same-domain/same-op_type operator with the HIGHEST version in the referenced operator sets.
repeated .onnx.OperatorSetIdProto opset_import = 8;
-
getOpsetImport
The OperatorSets this model relies on. All ModelProtos MUST have at least one entry that specifies which version of the ONNX OperatorSet is being imported. All nodes in the ModelProto's graph will bind against the operator with the same-domain/same-op_type operator with the HIGHEST version in the referenced operator sets.
repeated .onnx.OperatorSetIdProto opset_import = 8;
-
getOpsetImportCount
int getOpsetImportCount()The OperatorSets this model relies on. All ModelProtos MUST have at least one entry that specifies which version of the ONNX OperatorSet is being imported. All nodes in the ModelProto's graph will bind against the operator with the same-domain/same-op_type operator with the HIGHEST version in the referenced operator sets.
repeated .onnx.OperatorSetIdProto opset_import = 8;
-
getOpsetImportOrBuilderList
List<? extends Onnx.OperatorSetIdProtoOrBuilder> getOpsetImportOrBuilderList()The OperatorSets this model relies on. All ModelProtos MUST have at least one entry that specifies which version of the ONNX OperatorSet is being imported. All nodes in the ModelProto's graph will bind against the operator with the same-domain/same-op_type operator with the HIGHEST version in the referenced operator sets.
repeated .onnx.OperatorSetIdProto opset_import = 8;
-
getOpsetImportOrBuilder
The OperatorSets this model relies on. All ModelProtos MUST have at least one entry that specifies which version of the ONNX OperatorSet is being imported. All nodes in the ModelProto's graph will bind against the operator with the same-domain/same-op_type operator with the HIGHEST version in the referenced operator sets.
repeated .onnx.OperatorSetIdProto opset_import = 8;
-
hasProducerName
boolean hasProducerName()The name of the framework or tool used to generate this model. This field SHOULD be present to indicate which implementation/tool/framework emitted the model.
optional string producer_name = 2;
- Returns:
- Whether the producerName field is set.
-
getProducerName
String getProducerName()The name of the framework or tool used to generate this model. This field SHOULD be present to indicate which implementation/tool/framework emitted the model.
optional string producer_name = 2;
- Returns:
- The producerName.
-
getProducerNameBytes
com.google.protobuf.ByteString getProducerNameBytes()The name of the framework or tool used to generate this model. This field SHOULD be present to indicate which implementation/tool/framework emitted the model.
optional string producer_name = 2;
- Returns:
- The bytes for producerName.
-
hasProducerVersion
boolean hasProducerVersion()The version of the framework or tool used to generate this model. This field SHOULD be present to indicate which implementation/tool/framework emitted the model.
optional string producer_version = 3;
- Returns:
- Whether the producerVersion field is set.
-
getProducerVersion
String getProducerVersion()The version of the framework or tool used to generate this model. This field SHOULD be present to indicate which implementation/tool/framework emitted the model.
optional string producer_version = 3;
- Returns:
- The producerVersion.
-
getProducerVersionBytes
com.google.protobuf.ByteString getProducerVersionBytes()The version of the framework or tool used to generate this model. This field SHOULD be present to indicate which implementation/tool/framework emitted the model.
optional string producer_version = 3;
- Returns:
- The bytes for producerVersion.
-
hasDomain
boolean hasDomain()Domain name of the model. We use reverse domain names as name space indicators. For example: `com.facebook.fair` or `com.microsoft.cognitiveservices` Together with `model_version` and GraphProto.name, this forms the unique identity of the graph.
optional string domain = 4;
- Returns:
- Whether the domain field is set.
-
getDomain
String getDomain()Domain name of the model. We use reverse domain names as name space indicators. For example: `com.facebook.fair` or `com.microsoft.cognitiveservices` Together with `model_version` and GraphProto.name, this forms the unique identity of the graph.
optional string domain = 4;
- Returns:
- The domain.
-
getDomainBytes
com.google.protobuf.ByteString getDomainBytes()Domain name of the model. We use reverse domain names as name space indicators. For example: `com.facebook.fair` or `com.microsoft.cognitiveservices` Together with `model_version` and GraphProto.name, this forms the unique identity of the graph.
optional string domain = 4;
- Returns:
- The bytes for domain.
-
hasModelVersion
boolean hasModelVersion()The version of the graph encoded. See Version enum below.
optional int64 model_version = 5;
- Returns:
- Whether the modelVersion field is set.
-
getModelVersion
long getModelVersion()The version of the graph encoded. See Version enum below.
optional int64 model_version = 5;
- Returns:
- The modelVersion.
-
hasDocString
boolean hasDocString()A human-readable documentation for this model. Markdown is allowed.
optional string doc_string = 6;
- Returns:
- Whether the docString field is set.
-
getDocString
String getDocString()A human-readable documentation for this model. Markdown is allowed.
optional string doc_string = 6;
- Returns:
- The docString.
-
getDocStringBytes
com.google.protobuf.ByteString getDocStringBytes()A human-readable documentation for this model. Markdown is allowed.
optional string doc_string = 6;
- Returns:
- The bytes for docString.
-
hasGraph
boolean hasGraph()The parameterized graph that is evaluated to execute the model.
optional .onnx.GraphProto graph = 7;
- Returns:
- Whether the graph field is set.
-
getGraph
Onnx.GraphProto getGraph()The parameterized graph that is evaluated to execute the model.
optional .onnx.GraphProto graph = 7;
- Returns:
- The graph.
-
getGraphOrBuilder
Onnx.GraphProtoOrBuilder getGraphOrBuilder()The parameterized graph that is evaluated to execute the model.
optional .onnx.GraphProto graph = 7;
-
getMetadataPropsList
List<Onnx.StringStringEntryProto> getMetadataPropsList()Named metadata values; keys should be distinct.
repeated .onnx.StringStringEntryProto metadata_props = 14;
-
getMetadataProps
Named metadata values; keys should be distinct.
repeated .onnx.StringStringEntryProto metadata_props = 14;
-
getMetadataPropsCount
int getMetadataPropsCount()Named metadata values; keys should be distinct.
repeated .onnx.StringStringEntryProto metadata_props = 14;
-
getMetadataPropsOrBuilderList
List<? extends Onnx.StringStringEntryProtoOrBuilder> getMetadataPropsOrBuilderList()Named metadata values; keys should be distinct.
repeated .onnx.StringStringEntryProto metadata_props = 14;
-
getMetadataPropsOrBuilder
Named metadata values; keys should be distinct.
repeated .onnx.StringStringEntryProto metadata_props = 14;
-
getTrainingInfoList
List<Onnx.TrainingInfoProto> getTrainingInfoList()Training-specific information. Sequentially executing all stored `TrainingInfoProto.algorithm`s and assigning their outputs following the corresponding `TrainingInfoProto.update_binding`s is one training iteration. Similarly, to initialize the model (as if training hasn't happened), the user should sequentially execute all stored `TrainingInfoProto.initialization`s and assigns their outputs using `TrainingInfoProto.initialization_binding`s. If this field is empty, the training behavior of the model is undefined.
repeated .onnx.TrainingInfoProto training_info = 20;
-
getTrainingInfo
Training-specific information. Sequentially executing all stored `TrainingInfoProto.algorithm`s and assigning their outputs following the corresponding `TrainingInfoProto.update_binding`s is one training iteration. Similarly, to initialize the model (as if training hasn't happened), the user should sequentially execute all stored `TrainingInfoProto.initialization`s and assigns their outputs using `TrainingInfoProto.initialization_binding`s. If this field is empty, the training behavior of the model is undefined.
repeated .onnx.TrainingInfoProto training_info = 20;
-
getTrainingInfoCount
int getTrainingInfoCount()Training-specific information. Sequentially executing all stored `TrainingInfoProto.algorithm`s and assigning their outputs following the corresponding `TrainingInfoProto.update_binding`s is one training iteration. Similarly, to initialize the model (as if training hasn't happened), the user should sequentially execute all stored `TrainingInfoProto.initialization`s and assigns their outputs using `TrainingInfoProto.initialization_binding`s. If this field is empty, the training behavior of the model is undefined.
repeated .onnx.TrainingInfoProto training_info = 20;
-
getTrainingInfoOrBuilderList
List<? extends Onnx.TrainingInfoProtoOrBuilder> getTrainingInfoOrBuilderList()Training-specific information. Sequentially executing all stored `TrainingInfoProto.algorithm`s and assigning their outputs following the corresponding `TrainingInfoProto.update_binding`s is one training iteration. Similarly, to initialize the model (as if training hasn't happened), the user should sequentially execute all stored `TrainingInfoProto.initialization`s and assigns their outputs using `TrainingInfoProto.initialization_binding`s. If this field is empty, the training behavior of the model is undefined.
repeated .onnx.TrainingInfoProto training_info = 20;
-
getTrainingInfoOrBuilder
Training-specific information. Sequentially executing all stored `TrainingInfoProto.algorithm`s and assigning their outputs following the corresponding `TrainingInfoProto.update_binding`s is one training iteration. Similarly, to initialize the model (as if training hasn't happened), the user should sequentially execute all stored `TrainingInfoProto.initialization`s and assigns their outputs using `TrainingInfoProto.initialization_binding`s. If this field is empty, the training behavior of the model is undefined.
repeated .onnx.TrainingInfoProto training_info = 20;
-
getFunctionsList
List<Onnx.FunctionProto> getFunctionsList()A list of function protos local to the model. Name of the function "FunctionProto.name" should be unique within the domain "FunctionProto.domain". In case of any conflicts the behavior (whether the model local functions are given higher priority, or standard operator sets are given higher priotity or this is treated as error) is defined by the runtimes. The operator sets imported by FunctionProto should be compatible with the ones imported by ModelProto and other model local FunctionProtos. Example, if same operator set say 'A' is imported by a FunctionProto and ModelProto or by 2 FunctionProtos then versions for the operator set may be different but, the operator schema returned for op_type, domain, version combination for both the versions should be same for every node in the function body. One FunctionProto can reference other FunctionProto in the model, however, recursive reference is not allowed.
repeated .onnx.FunctionProto functions = 25;
-
getFunctions
A list of function protos local to the model. Name of the function "FunctionProto.name" should be unique within the domain "FunctionProto.domain". In case of any conflicts the behavior (whether the model local functions are given higher priority, or standard operator sets are given higher priotity or this is treated as error) is defined by the runtimes. The operator sets imported by FunctionProto should be compatible with the ones imported by ModelProto and other model local FunctionProtos. Example, if same operator set say 'A' is imported by a FunctionProto and ModelProto or by 2 FunctionProtos then versions for the operator set may be different but, the operator schema returned for op_type, domain, version combination for both the versions should be same for every node in the function body. One FunctionProto can reference other FunctionProto in the model, however, recursive reference is not allowed.
repeated .onnx.FunctionProto functions = 25;
-
getFunctionsCount
int getFunctionsCount()A list of function protos local to the model. Name of the function "FunctionProto.name" should be unique within the domain "FunctionProto.domain". In case of any conflicts the behavior (whether the model local functions are given higher priority, or standard operator sets are given higher priotity or this is treated as error) is defined by the runtimes. The operator sets imported by FunctionProto should be compatible with the ones imported by ModelProto and other model local FunctionProtos. Example, if same operator set say 'A' is imported by a FunctionProto and ModelProto or by 2 FunctionProtos then versions for the operator set may be different but, the operator schema returned for op_type, domain, version combination for both the versions should be same for every node in the function body. One FunctionProto can reference other FunctionProto in the model, however, recursive reference is not allowed.
repeated .onnx.FunctionProto functions = 25;
-
getFunctionsOrBuilderList
List<? extends Onnx.FunctionProtoOrBuilder> getFunctionsOrBuilderList()A list of function protos local to the model. Name of the function "FunctionProto.name" should be unique within the domain "FunctionProto.domain". In case of any conflicts the behavior (whether the model local functions are given higher priority, or standard operator sets are given higher priotity or this is treated as error) is defined by the runtimes. The operator sets imported by FunctionProto should be compatible with the ones imported by ModelProto and other model local FunctionProtos. Example, if same operator set say 'A' is imported by a FunctionProto and ModelProto or by 2 FunctionProtos then versions for the operator set may be different but, the operator schema returned for op_type, domain, version combination for both the versions should be same for every node in the function body. One FunctionProto can reference other FunctionProto in the model, however, recursive reference is not allowed.
repeated .onnx.FunctionProto functions = 25;
-
getFunctionsOrBuilder
A list of function protos local to the model. Name of the function "FunctionProto.name" should be unique within the domain "FunctionProto.domain". In case of any conflicts the behavior (whether the model local functions are given higher priority, or standard operator sets are given higher priotity or this is treated as error) is defined by the runtimes. The operator sets imported by FunctionProto should be compatible with the ones imported by ModelProto and other model local FunctionProtos. Example, if same operator set say 'A' is imported by a FunctionProto and ModelProto or by 2 FunctionProtos then versions for the operator set may be different but, the operator schema returned for op_type, domain, version combination for both the versions should be same for every node in the function body. One FunctionProto can reference other FunctionProto in the model, however, recursive reference is not allowed.
repeated .onnx.FunctionProto functions = 25;
-