Code covered by the BSD License  

Highlights from
Statistical Learning Toolbox

from Statistical Learning Toolbox by Dahua Lin
Functions for statistical learning, pattern recognition and computer vision, covering many topics.

Description of slmetric_pw_blks
Home > sltoolbox > core > slmetric_pw_blks.m

slmetric_pw_blks

PURPOSE ^

SLMETRIC_PW_BLKS Compute the pairwise metrics in a blockwise manner

SYNOPSIS ^

function slmetric_pw_blks(X1, X2, ps, dstpath, mtype, varargin)

DESCRIPTION ^

SLMETRIC_PW_BLKS Compute the pairwise metrics in a blockwise manner

 $ Syntax $
   - slmetric_pw_blks(X1, X2, ps, dstpath, mtype, ...)

 $ Arguments $
   - X1:       the first sample matrix
   - X2:       the second sample matrix
   - ps:       the partition structure of the score matrix
   - dstpath:  the destination path
   - mtype:    the metric type

 $ Description $
   - slmetric_pw_blks(X1, X2, ps, dstpath, mtype, ...) computes the 
     pairwise metric values for large dataset in blockwise manner.
     Each block of scores are computed respectively and stored in files.
     This function is an extension of slmetric_pw to support 
     blockwise score computation. 
     Please refer to slmetric_pw and slpwcomp_blks for more information
     on the usage.

 $ History $
   - Created by Dahua Lin, on Aug 9th, 2006

CROSS-REFERENCE INFORMATION ^

This function calls:
  • slpwcomp_blks SLPWCOMP_BLKS Computes pairwise value matrix
  • raise_lackinput RAISE_LACKINPUT Raises an error indicating lack of input argument
This function is called by:

SOURCE CODE ^

0001 function slmetric_pw_blks(X1, X2, ps, dstpath, mtype, varargin)
0002 %SLMETRIC_PW_BLKS Compute the pairwise metrics in a blockwise manner
0003 %
0004 % $ Syntax $
0005 %   - slmetric_pw_blks(X1, X2, ps, dstpath, mtype, ...)
0006 %
0007 % $ Arguments $
0008 %   - X1:       the first sample matrix
0009 %   - X2:       the second sample matrix
0010 %   - ps:       the partition structure of the score matrix
0011 %   - dstpath:  the destination path
0012 %   - mtype:    the metric type
0013 %
0014 % $ Description $
0015 %   - slmetric_pw_blks(X1, X2, ps, dstpath, mtype, ...) computes the
0016 %     pairwise metric values for large dataset in blockwise manner.
0017 %     Each block of scores are computed respectively and stored in files.
0018 %     This function is an extension of slmetric_pw to support
0019 %     blockwise score computation.
0020 %     Please refer to slmetric_pw and slpwcomp_blks for more information
0021 %     on the usage.
0022 %
0023 % $ History $
0024 %   - Created by Dahua Lin, on Aug 9th, 2006
0025 %
0026 
0027 if nargin < 5
0028     raise_lackinput('slmetric_pw_blks', 5);
0029 end
0030 
0031 slpwcomp_blks(X1, X2, ps, dstpath, 'slmetric_pw', mtype, varargin{:});

Generated on Wed 20-Sep-2006 12:43:11 by m2html © 2003

Contact us at files@mathworks.com