http://imagej.273.s1.nabble.com/Trainable-Weka-Exception-1083-error-tp5010343p5010356.html
There was indeed a bug produced whenever the input image was a stack but no
samples were traced in its first slice. This is fixed now in the latest
> Hello Douglas,
>
> This is odd. Are you using an input image of 214 slices and only 1 feature
> selected?
>
> Can you send me the input image with the selections or at least a
> screenshot so I can see what's going on?
>
> Thanks in advance!
>
> ignacio
>
> On Sun, Nov 9, 2014 at 10:25 PM, Douglas Benn <
[hidden email]>
> wrote:
>
>> I would be grateful for advice regarding
>> java.lang.ArrayindexOutOfBoundsException: 1083
>>
>> I was Training on a set of Class 1 and Class 2 features I had created
>> using Wand in ImageJ. I started the training and the Log trace showed
>>
>> Feature stack array updated (214 slices, 1 feature 189 seconds)
>> # class 1 pixels 82990
>> # class 2 pixels 70279
>> Creating training data took 27 secs
>> Training classifier did not finish.
>>
>> In an error window it reported java.lang.ArrayindexOutOfBoundsException:
>> 1083
>>
>> I am using an iMac 27" with 8 GB RAM and Windows 7 running under
>> Bootcamp. ImageJ runs fine and this is the first time I have had this
>> problem and only with WEKA which I started using today. I am calling Weka
>> from the Plugins > Segmentation > Trainable Weka Segmentation
>>
>> Thank you for any advice.
>>
>> Douglas Benn
>>
>> --
>> ImageJ mailing list:
http://imagej.nih.gov/ij/list.html>>
>
>
>
> --
> Ignacio Arganda-Carreras, Ph.D.
> Seung's lab, 46-5065
> Department of Brain and Cognitive Sciences
> Massachusetts Institute of Technology
> 43 Vassar St.
> Cambridge, MA 02139
> USA
>
> Phone: (001) 617-324-3747
> Website:
http://bioweb.cnb.csic.es/~iarganda/index_EN.html>