Class DnnSuperResImpl


  • public class DnnSuperResImpl
    extends java.lang.Object
    A class to upscale images via convolutional neural networks. The following four models are implemented:
    • edsr
    • espcn
    • fsrcnn
    • lapsrn
    • Field Detail

      • nativeObj

        protected final long nativeObj
    • Constructor Detail

      • DnnSuperResImpl

        protected DnnSuperResImpl​(long addr)
    • Method Detail

      • getNativeObjAddr

        public long getNativeObjAddr()
      • create

        public static DnnSuperResImpl create()
        Empty constructor for python
        Returns:
        automatically generated
      • readModel

        public void readModel​(java.lang.String path)
        Read the model from the given path
        Parameters:
        path - Path to the model file.
      • setModel

        public void setModel​(java.lang.String algo,
                             int scale)
        Set desired model
        Parameters:
        algo - String containing one of the desired models:
        • __edsr__
        • __espcn__
        • __fsrcnn__
        • __lapsrn__
        scale - Integer specifying the upscale factor
      • setPreferableBackend

        public void setPreferableBackend​(int backendId)
        Set computation backend
        Parameters:
        backendId - automatically generated
      • setPreferableTarget

        public void setPreferableTarget​(int targetId)
        Set computation target
        Parameters:
        targetId - automatically generated
      • upsample

        public void upsample​(Mat img,
                             Mat result)
        Upsample via neural network
        Parameters:
        img - Image to upscale
        result - Destination upscaled image
      • upsampleMultioutput

        public void upsampleMultioutput​(Mat img,
                                        java.util.List<Mat> imgs_new,
                                        MatOfInt scale_factors,
                                        java.util.List<java.lang.String> node_names)
        Upsample via neural network of multiple outputs
        Parameters:
        img - Image to upscale
        imgs_new - Destination upscaled images
        scale_factors - Scaling factors of the output nodes
        node_names - Names of the output nodes in the neural network
      • getScale

        public int getScale()
        Returns the scale factor of the model:
        Returns:
        Current scale factor.
      • getAlgorithm

        public java.lang.String getAlgorithm()
        Returns the scale factor of the model:
        Returns:
        Current algorithm.
      • finalize

        protected void finalize()
                         throws java.lang.Throwable
        Overrides:
        finalize in class java.lang.Object
        Throws:
        java.lang.Throwable