ort functions

The table below lists all the ort built-in functions (in this namespace: ).

onnxruntime library integration, enabling MarkLogic server to load and evaluate ONNX models.

19 functions
Function name Description
ort.getValue For an ort.value with value type "SEQUENCE", returns the ort.value at specified index; for value type "MAP", index 0 returns the key, and index 1 returns the value.
ort.map Creates a value with type "MAP", using an ort.value as key and an ort.value as value.
ort.run Perform inference of a session, based on supplied input values.
ort.sequence Creates a value with type "SEQUENCE".
ort.session Load an ONNX model from the database, as an inference session.
ort.sessionInputCount Returns the number of inputs of a session.
ort.sessionInputName Returns the name of an input of a session, specified by an index.
ort.sessionInputType Returns a Map containing the type information of an input of a session, specified by an index.
ort.sessionOutputCount Returns the number of outputs of a session.
ort.sessionOutputName Returns the name of an output of a session, specified by an index.
ort.sessionOutputType Returns a Map containing the type information of an output of a session, specified by an index.
ort.string Creates a string tensor.
ort.stringContent Returns the content of a string tensor.
ort.value Constructs an ort.value to be supplied to an ort.session to perform inference.
ort.valueCount Returns the number of ort.value in an ort.value with value type "SEQUENCE", and always return 2 for "MAP".
ort.valueGetArray Returns the tensor represented by the ort.value as a flattened one-dimensional array.
ort.valueGetShape Returns the shape of the ort.value as an Array.
ort.valueGetType Returns the tensor element type of the ort.value as a String.
ort.valueIsTensor Returns if the ort.value has value type "TENSOR".
Powered by MarkLogic Server | Terms of Use | Privacy Policy