Models
ModelProto is a top-level file/container format for bundling a ML model and associating its computation graph with metadata.
The semantics of the model are described by the associated GraphProto's.
Value parameters
- docString
-
A human-readable documentation for this model. Markdown is allowed.
- domain
-
Domain name of the model. We use reverse domain names as name space indicators. For example:
com.facebook.fair
orcom.microsoft.cognitiveservices
Together withmodel_version
and GraphProto.name, this forms the unique identity of the graph. - graph
-
The parameterized graph that is evaluated to execute the model.
- irVersion
-
The version of the IR this model targets. See Version enum above. This field MUST be present.
- metadataProps
-
Named metadata values; keys should be distinct.
- modelVersion
-
The version of the graph encoded. See Version enum below.
- opsetImport
-
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.
- producerName
-
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.
- producerVersion
-
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.
- trainingInfo
-
Training-specific information. Sequentially executing all stored
TrainingInfoProto.algorithm
s and assigning their outputs following the correspondingTrainingInfoProto.update_binding
s is one training iteration. Similarly, to initialize the model (as if training hasn't happened), the user should sequentially execute all storedTrainingInfoProto.initialization
s and assigns their outputs usingTrainingInfoProto.initialization_binding
s. If this field is empty, the training behavior of the model is undefined.
Attributes
- Companion
- object
- Graph
-
- Supertypes
-
trait Updatable[ModelProto]trait GeneratedMessagetrait Serializabletrait Producttrait Equalsclass Objecttrait Matchableclass Any