onnx.onnx.NodeProto
See theNodeProto companion object
final case class NodeProto(input: Seq[String], output: Seq[String], name: Option[String], opType: Option[String], domain: Option[String], attribute: Seq[AttributeProto], docString: Option[String], unknownFields: UnknownFieldSet) extends GeneratedMessage, Updatable[NodeProto]
Nodes
Computation graphs are made up of a DAG of nodes, which represent what is commonly called a "layer" or "pipeline stage" in machine learning frameworks.
For example, it can be a node of type "Conv" that takes in an image, a filter tensor and a bias tensor, and produces the convolved output.
Value parameters
- attribute
-
Additional named attributes.
- docString
-
A human-readable documentation for this node. Markdown is allowed.
- domain
-
The domain of the OperatorSet that specifies the operator named by op_type. namespace Domain
- input
-
namespace Value
- name
-
An optional identifier for this node in a graph. This field MAY be absent in ths version of the IR. namespace Node
- opType
-
The symbolic identifier of the Operator to execute. namespace Operator
- output
-
namespace Value
Attributes
Members list
In this article