Represents the classification results of a model. Typically used as a result for classification tasks.
Public Constructors
Public Methods
abstract List<Classifications> |
classifications()
The classification results for each head of the model.
|
static ClassificationResult |
create(List<Classifications> classifications, Optional<Long> timestampMs)
Creates a
ClassificationResult instance. |
static ClassificationResult |
createFromProto(ClassificationsProto.ClassificationResult proto)
Creates a
ClassificationResult object from a ERROR(/ClassificationsProto.ClassificationResult) protobuf message. |
abstract Optional<Long> |
timestampMs()
The optional timestamp (in milliseconds) of the start of the chunk of data corresponding to
these results.
|
Inherited Methods
Public Constructors
public ClassificationResult ()
Public Methods
public abstract List<Classifications> classifications ()
The classification results for each head of the model.
public static ClassificationResult create (List<Classifications> classifications, Optional<Long> timestampMs)
Creates a ClassificationResult
instance.
Parameters
classifications | the list of Classifications objects containing the predicted
categories for each head of the model. |
---|---|
timestampMs | the optional timestamp (in milliseconds) of the start of the chunk of data corresponding to these results. |
public static ClassificationResult createFromProto (ClassificationsProto.ClassificationResult proto)
Creates a ClassificationResult
object from a ERROR(/ClassificationsProto.ClassificationResult)
protobuf message.
Parameters
proto | the ERROR(/ClassificationsProto.ClassificationResult) protobuf message to convert.
|
---|
public abstract Optional<Long> timestampMs ()
The optional timestamp (in milliseconds) of the start of the chunk of data corresponding to these results.
This is only used for classification on time series (e.g. audio classification). In these use cases, the amount of data to process might exceed the maximum size that the model can process: to solve this, the input data is split into multiple chunks starting at different timestamps.