[ITK-users] (no subject)

[Carmine Pagliaro]

very very complicated

2015-10-31 17:51 GMT+01:00 Carmine Pagliaro <carminepagliaro at gmail.com>:

> ok
>
> 2015-10-31 17:49 GMT+01:00 Matt McCormick <matt.mccormick at kitware.com>:
>
>> Hi Carmine,
>>
>> Use the existing optimizer classes as an example, and examine the API
>> and its descriptions in the Doxygen documentation.
>>
>> HTH,
>> Matt
>>
>> On Sat, Oct 31, 2015 at 12:07 PM, Carmine Pagliaro
>> <carminepagliaro at gmail.com> wrote:
>> > oh yes but, I would know how can I create a new one. i.e
>> > RegularStepGradientDescentBaseOptimizer becomes MyPersonalOptimizer. in
>> this
>> > class i'll write my personal algorithm.
>> >
>> > 2015-10-31 16:54 GMT+01:00 Dženan Zukić <dzenanz at gmail.com>:
>> >>
>> >> You should probably look at one of the registration examples to see
>> how an
>> >> optimizer is used:
>> >> http://itk.org/Wiki/ITK/Examples/Included/Registration
>> >>
>> >> HTH
>> >>
>> >> On Sat, Oct 31, 2015 at 7:07 AM, Carmine Pagliaro
>> >> <carminepagliaro at gmail.com> wrote:
>> >>>
>> >>> Thank you for the reply, Dr. McCormick.
>> >>> But that not help me.
>> >>> I don't understand how I can create a new optimizer algorithm and
>> pass it
>> >>> to the registration->SetOptimizer() method
>> >>>
>> >>>
>> >>> 2015-10-30 17:02 GMT+01:00 Matt McCormick <matt.mccormick at kitware.com
>> >:
>> >>>>
>> >>>> Hi Carmine,
>> >>>>
>> >>>> To see all the optimizer options, go to the base class in Doxygen:
>> >>>>
>> >>>>
>> >>>>
>> http://www.itk.org/Doxygen/html/classitk_1_1SingleValuedNonLinearOptimizer.html
>> >>>>
>> >>>> Then, look at the inheritance diagram.  There are options like the
>> >>>> OnePlusOneEvolutionaryOptimizer and ParticleSwarmOptimizer.
>> >>>>
>> >>>> Hope this helps,
>> >>>> Matt
>> >>>>
>> >>>> On Fri, Oct 30, 2015 at 10:59 AM, Carmine Pagliaro
>> >>>> <carminepagliaro at gmail.com> wrote:
>> >>>> > Dear ITK team,
>> >>>> >
>> >>>> > in the file attacched I register 2 mri image in nifti format.
>> >>>> >
>> >>>> > the optimization algorithm is gradientdescent
>> >>>> >
>> >>>> > typedef itk::RegularStepGradientDescentOptimizer
>>  OptimizerType;
>> >>>> >
>> >>>> > I would make one myself using annealing. so how can I do this?
>> >>>> >
>> >>>> > how could I must modified the follow code ? what is optimizer?
>> >>>> >
>> >>>> > OptimizerType::Pointer      optimizer     = OptimizerType::New();
>> >>>> > registration->SetOptimizer(     optimizer     );
>> >>>> >
>> >>>> > thank you very much
>> >>>> > --
>> >>>> > Carmine Pagliaro
>> >>>> > Life is for sharing.
>> >>>> >
>> >>>> >
>> >>>> > _____________________________________
>> >>>> > Powered by www.kitware.com
>> >>>> >
>> >>>> > Visit other Kitware open-source projects at
>> >>>> > http://www.kitware.com/opensource/opensource.html
>> >>>> >
>> >>>> > Kitware offers ITK Training Courses, for more information visit:
>> >>>> > http://www.kitware.com/products/protraining.php
>> >>>> >
>> >>>> > Please keep messages on-topic and check the ITK FAQ at:
>> >>>> > http://www.itk.org/Wiki/ITK_FAQ
>> >>>> >
>> >>>> > Follow this link to subscribe/unsubscribe:
>> >>>> > http://public.kitware.com/mailman/listinfo/insight-users
>> >>>> >
>> >>>
>> >>>
>> >>>
>> >>>
>> >>> --
>> >>> Carmine Pagliaro
>> >>> Life is for sharing.
>> >>>
>> >>>
>> >>> _____________________________________
>> >>> Powered by www.kitware.com
>> >>>
>> >>> Visit other Kitware open-source projects at
>> >>> http://www.kitware.com/opensource/opensource.html
>> >>>
>> >>> Kitware offers ITK Training Courses, for more information visit:
>> >>> http://www.kitware.com/products/protraining.php
>> >>>
>> >>> Please keep messages on-topic and check the ITK FAQ at:
>> >>> http://www.itk.org/Wiki/ITK_FAQ
>> >>>
>> >>> Follow this link to subscribe/unsubscribe:
>> >>> http://public.kitware.com/mailman/listinfo/insight-users
>> >>>
>> >>
>> >
>> >
>> >
>> > --
>> > Carmine Pagliaro
>> > Life is for sharing.
>> >
>>
>
>
>
> --
> Carmine Pagliaro
> *Life is for sharing.*
>
>


-- 
Carmine Pagliaro
*Life is for sharing.*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20151101/2fed6299/attachment.html>