Package org.deeplearning4j.parallelism.inference

Interface InferenceObservable

    • Method Summary

      All Methods Instance Methods Abstract Methods 
      Modifier and Type Method Description
      void addInput​(org.nd4j.linalg.api.ndarray.INDArray... input)  
      void addInput​(org.nd4j.linalg.api.ndarray.INDArray[] input, org.nd4j.linalg.api.ndarray.INDArray[] inputMasks)  
      void addObserver​(Observer observer)  
      List<org.nd4j.common.primitives.Pair<org.nd4j.linalg.api.ndarray.INDArray[],​org.nd4j.linalg.api.ndarray.INDArray[]>> getInputBatches()
      Get input batches - and their associated input mask arrays, if any
      Note that usually the returned list will be of size 1 - however, in the batched case, not all inputs can actually be batched (variable size inputs to fully convolutional net, for example).
      org.nd4j.linalg.api.ndarray.INDArray[] getOutput()  
      void setOutputBatches​(List<org.nd4j.linalg.api.ndarray.INDArray[]> output)  
      void setOutputException​(Exception e)  

    • Method Detail

      • getInputBatches

        List<org.nd4j.common.primitives.Pair<org.nd4j.linalg.api.ndarray.INDArray[],​org.nd4j.linalg.api.ndarray.INDArray[]>> getInputBatches()
        Get input batches - and their associated input mask arrays, if any
        Note that usually the returned list will be of size 1 - however, in the batched case, not all inputs can actually be batched (variable size inputs to fully convolutional net, for example). In these "can't batch" cases, multiple input batches will be returned, to be processed
        Returns:
        List of pairs of input arrays and input mask arrays. Input mask arrays may be null.

      • addInput

        void addInput​(org.nd4j.linalg.api.ndarray.INDArray... input)

      • addInput

        void addInput​(org.nd4j.linalg.api.ndarray.INDArray[] input,
              org.nd4j.linalg.api.ndarray.INDArray[] inputMasks)

      • setOutputBatches

        void setOutputBatches​(List<org.nd4j.linalg.api.ndarray.INDArray[]> output)

      • setOutputException

        void setOutputException​(Exception e)

      • addObserver

        void addObserver​(Observer observer)

      • getOutput

        org.nd4j.linalg.api.ndarray.INDArray[] getOutput()