Package tensorflow.serving

Interface Predict.PredictStreamedOptionsOrBuilder

All Superinterfaces:
com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder
All Known Implementing Classes:
Predict.PredictStreamedOptions, Predict.PredictStreamedOptions.Builder
Enclosing class:
Predict
public static interface Predict.PredictStreamedOptionsOrBuilder extends com.google.protobuf.MessageOrBuilder

  • Method Details

    • getRequestStateValue

      int getRequestStateValue()
       Request state used to handle segmentation of requests.
      .tensorflow.serving.PredictStreamedOptions.RequestState request_state = 1;
      Returns:
      The enum numeric value on the wire for requestState.

    • getRequestState

      Predict.PredictStreamedOptions.RequestState getRequestState()
       Request state used to handle segmentation of requests.
      .tensorflow.serving.PredictStreamedOptions.RequestState request_state = 1;
      Returns:
      The requestState.

    • getSplitDimensionsCount

      int getSplitDimensionsCount()
       Input tensors split dimensions.
 Defines the dimension used to split input tensors specified
 in PredictRequest.inputs. The dimension will be used
 for concatenation of multiple SPLIT requests.

 For input tensor in PredictRequest.inputs that are not contained in this
 map, the tensors from the first SPLIT request will be used.

 For example, with an original input tensor of [[1, 2, 3, 4], [5, 6, 7, 8]].

 For a split dimension of 0 and two requests (SPLIT and END_SPLIT), the
 input tensors for request 1 should be [1, 2, 3, 4] and request 2 should be
 be [5, 6, 7, 8].

 For a split dimension of 1 and two requests (SPLIT and END_SPLIT), the
 input tensors for request 1 should be [[1, 2], [5, 6]] and request 2 should
 be [[3, 4], [7, 8]].
      map<string, int32> split_dimensions = 2;

    • containsSplitDimensions

      boolean containsSplitDimensions(String key)
       Input tensors split dimensions.
 Defines the dimension used to split input tensors specified
 in PredictRequest.inputs. The dimension will be used
 for concatenation of multiple SPLIT requests.

 For input tensor in PredictRequest.inputs that are not contained in this
 map, the tensors from the first SPLIT request will be used.

 For example, with an original input tensor of [[1, 2, 3, 4], [5, 6, 7, 8]].

 For a split dimension of 0 and two requests (SPLIT and END_SPLIT), the
 input tensors for request 1 should be [1, 2, 3, 4] and request 2 should be
 be [5, 6, 7, 8].

 For a split dimension of 1 and two requests (SPLIT and END_SPLIT), the
 input tensors for request 1 should be [[1, 2], [5, 6]] and request 2 should
 be [[3, 4], [7, 8]].
      map<string, int32> split_dimensions = 2;

    • getSplitDimensions

      @Deprecated Map<String,Integer> getSplitDimensions()
      Deprecated.
      Use getSplitDimensionsMap() instead.

    • getSplitDimensionsMap

      Map<String,Integer> getSplitDimensionsMap()
       Input tensors split dimensions.
 Defines the dimension used to split input tensors specified
 in PredictRequest.inputs. The dimension will be used
 for concatenation of multiple SPLIT requests.

 For input tensor in PredictRequest.inputs that are not contained in this
 map, the tensors from the first SPLIT request will be used.

 For example, with an original input tensor of [[1, 2, 3, 4], [5, 6, 7, 8]].

 For a split dimension of 0 and two requests (SPLIT and END_SPLIT), the
 input tensors for request 1 should be [1, 2, 3, 4] and request 2 should be
 be [5, 6, 7, 8].

 For a split dimension of 1 and two requests (SPLIT and END_SPLIT), the
 input tensors for request 1 should be [[1, 2], [5, 6]] and request 2 should
 be [[3, 4], [7, 8]].
      map<string, int32> split_dimensions = 2;

    • getSplitDimensionsOrDefault

      int getSplitDimensionsOrDefault(String key, int defaultValue)
       Input tensors split dimensions.
 Defines the dimension used to split input tensors specified
 in PredictRequest.inputs. The dimension will be used
 for concatenation of multiple SPLIT requests.

 For input tensor in PredictRequest.inputs that are not contained in this
 map, the tensors from the first SPLIT request will be used.

 For example, with an original input tensor of [[1, 2, 3, 4], [5, 6, 7, 8]].

 For a split dimension of 0 and two requests (SPLIT and END_SPLIT), the
 input tensors for request 1 should be [1, 2, 3, 4] and request 2 should be
 be [5, 6, 7, 8].

 For a split dimension of 1 and two requests (SPLIT and END_SPLIT), the
 input tensors for request 1 should be [[1, 2], [5, 6]] and request 2 should
 be [[3, 4], [7, 8]].
      map<string, int32> split_dimensions = 2;

    • getSplitDimensionsOrThrow

      int getSplitDimensionsOrThrow(String key)
       Input tensors split dimensions.
 Defines the dimension used to split input tensors specified
 in PredictRequest.inputs. The dimension will be used
 for concatenation of multiple SPLIT requests.

 For input tensor in PredictRequest.inputs that are not contained in this
 map, the tensors from the first SPLIT request will be used.

 For example, with an original input tensor of [[1, 2, 3, 4], [5, 6, 7, 8]].

 For a split dimension of 0 and two requests (SPLIT and END_SPLIT), the
 input tensors for request 1 should be [1, 2, 3, 4] and request 2 should be
 be [5, 6, 7, 8].

 For a split dimension of 1 and two requests (SPLIT and END_SPLIT), the
 input tensors for request 1 should be [[1, 2], [5, 6]] and request 2 should
 be [[3, 4], [7, 8]].
      map<string, int32> split_dimensions = 2;

    • getReturnSingleResponse

      boolean getReturnSingleResponse()
       If true, there will be a single PredictResponse output.
 If false, output can be split into 1 or more PredictResponses.
 Value of this field should be the same for all requests in the stream.
      bool return_single_response = 3;
      Returns:
      The returnSingleResponse.