usage: prog [options] <input stack>
Performs k-means classification on a stack of aligned input images or invariants generated
from the input images. eg - if images are unaligned one option is to use the --fp option in 
e2proc2d.py to generate invariants which can then be classified. 

This program should not be confused with the k-means processor which provides a mechanism
for grouping pixels in a single map into regions. This program classifies similar images

Option Type Description
--version None show program's version number and exit
--ncls, -N int Number of classes to generate
--average, -A None Average the particles within each class
--sigma None with --average, this will also produce standard deviation images for each average
--onein None Read 1-d input images from a single 2-D image (oneout in e2basis.py, default out e2msa.py)
--oneinali None Read 1-d input images from a single 2-D image where the first 4 elements on each row are da,dx,dy,flip
--normavg None Normalize averages
--clsmx str Standard EMAN2 output suitable for use with e2classaverage, etc.
--clsfiles, -C None Write EMAN 1 style cls files with members of each class
--mininclass int Try to eliminate classes with fewer than specified members. Default=2
--outlierclass None If selected, classes with fewer than mininclass particles will move permanently to an outlier class (the last class)
--original, -O str If the input stack was derived from another stack, you can provide the name of the original stack here
--axes str Works only for 1-D input images. Specify a range, eg 0-5 to indicate which components to use from each vector. Inclusive. default=all
--exclude str The named file should contain a set of integers, each representing an image from the input file to exclude.
--minchange int Minimum number of particles that change group before deicding to terminate. Default = len(data)/(#cls*25)
--fastseed None Will seed the k-means loop quickly, but may produce lest consistent results.
--ppid int Set the PID of the parent process, used for cross platform PPID
--verbose, -v int verbose level [0-9], higher number means higher level of verboseness