interface publique SignatureDefOrBuilder
Sous-classes indirectes connues |
Méthodes publiques
booléen abstrait | containInputs (clé de chaîne) Named input parameters. |
booléen abstrait | contient des sorties (clé de chaîne) Named output parameters. |
Carte abstraite<String, TensorInfo > | getInputs () Utilisez plutôt getInputsMap() . |
abstrait entier | getInputsCount () Named input parameters. |
Carte abstraite<String, TensorInfo > | getInputsMap () Named input parameters. |
résumé TensorInfo | |
résumé TensorInfo | getInputsOrThrow (clé de chaîne) Named input parameters. |
chaîne abstraite | getMethodName () Extensible method_name information enabling third-party users to mark a SignatureDef as supporting a particular method. |
résumé com.google.protobuf.ByteString | getMethodNameBytes () Extensible method_name information enabling third-party users to mark a SignatureDef as supporting a particular method. |
Carte abstraite<String, TensorInfo > | getOutputs () Utilisez plutôt getOutputsMap() . |
abstrait entier | getOutputsCount () Named output parameters. |
Carte abstraite<String, TensorInfo > | getOutputsMap () Named output parameters. |
résumé TensorInfo | |
résumé TensorInfo | getOutputsOrThrow (clé de chaîne) Named output parameters. |
Méthodes publiques
public abstrait booléen containInputs (clé de chaîne)
Named input parameters.
map<string, .tensorflow.TensorInfo> inputs = 1;
public abstrait booléen containOutputs (clé de chaîne)
Named output parameters.
map<string, .tensorflow.TensorInfo> outputs = 2;
public abstrait int getInputsCount ()
Named input parameters.
map<string, .tensorflow.TensorInfo> inputs = 1;
public abstrait Map<String, TensorInfo > getInputsMap ()
Named input parameters.
map<string, .tensorflow.TensorInfo> inputs = 1;
résumé public TensorInfo getInputsOrDefault (clé de chaîne, TensorInfo defaultValue)
Named input parameters.
map<string, .tensorflow.TensorInfo> inputs = 1;
résumé public TensorInfo getInputsOrThrow (clé de chaîne)
Named input parameters.
map<string, .tensorflow.TensorInfo> inputs = 1;
chaîne abstraite publique getMethodName ()
Extensible method_name information enabling third-party users to mark a SignatureDef as supporting a particular method. This enables producers and consumers of SignatureDefs, e.g. a model definition library and a serving library to have a clear hand-off regarding the semantics of a computation. Note that multiple SignatureDefs in a single MetaGraphDef may have the same method_name. This is commonly used to support multi-headed computation, where a single graph computation may return multiple results.
string method_name = 3;
résumé public com.google.protobuf.ByteString getMethodNameBytes ()
Extensible method_name information enabling third-party users to mark a SignatureDef as supporting a particular method. This enables producers and consumers of SignatureDefs, e.g. a model definition library and a serving library to have a clear hand-off regarding the semantics of a computation. Note that multiple SignatureDefs in a single MetaGraphDef may have the same method_name. This is commonly used to support multi-headed computation, where a single graph computation may return multiple results.
string method_name = 3;
public abstrait int getOutputsCount ()
Named output parameters.
map<string, .tensorflow.TensorInfo> outputs = 2;
public abstrait Map<String, TensorInfo > getOutputsMap ()
Named output parameters.
map<string, .tensorflow.TensorInfo> outputs = 2;
résumé public TensorInfo getOutputsOrDefault (clé de chaîne, TensorInfo defaultValue)
Named output parameters.
map<string, .tensorflow.TensorInfo> outputs = 2;
résumé public TensorInfo getOutputsOrThrow (clé de chaîne)
Named output parameters.
map<string, .tensorflow.TensorInfo> outputs = 2;