predict

Type Members

1. final case class PredictRequest(modelSpec: Option[ModelSpec] = None, inputs: Map[String, TensorProto] = ..., outputFilter: Seq[String] = _root_.scala.collection.Seq.empty) extends GeneratedMessage with Message[PredictRequest] with Updatable[PredictRequest] with Product with Serializable

   

   PredictRequest specifies which TensorFlow model to run, as well as how inputs are mapped to tensors and how outputs are filtered before returning to user.

   PredictRequest specifies which TensorFlow model to run, as well as how inputs are mapped to tensors and how outputs are filtered before returning to user.

   modelSpec

   Model Specification.

   inputs

   Input tensors. Names of input tensor are alias names. The mapping from aliases to real input tensor names is stored in the SavedModel export as a prediction SignatureDef under the 'inputs' field.

   outputFilter

   Output filter. Names specified are alias names. The mapping from aliases to real output tensor names is stored in the SavedModel export as a prediction SignatureDef under the 'outputs' field. Only tensors specified here will be run/fetched and returned, with the exception that when none is specified, all tensors specified in the named signature will be run/fetched and returned.

   Annotations

   @SerialVersionUID()

2. final case class PredictResponse(outputs: Map[String, TensorProto] = ...) extends GeneratedMessage with Message[PredictResponse] with Updatable[PredictResponse] with Product with Serializable

   

   Response for PredictRequest on successful run.

   Response for PredictRequest on successful run.

   outputs

   Output tensors.

   Annotations

   @SerialVersionUID()