[Insight-users] Question about RegularStepGradientDescentOptimizer

[Luis Ibanez]

Hi Feng,

This depends on the ImageMetric that you are using.

Some metric may give values that are better when the overlap
between the images decreases. If you are using such a metric
you may end up in a situation where the derivatives of the
metric indicate that moving the images apart will give you
a better (numeric) match.

What metric are you using ?



In any case, a initial step length of 20.0 is way too large.
If you are applying the scaling parameters correctly you should
have an optimization space in the range of 0.0 to 1.0.

You may want to try reducing your step length to  something like
1.0 and then monitor how much the metric is changing.


   Regards,


      Luis


-----------------------
Feng Qiao wrote:

> Hi,
> I tried to use the RegularStepGradientDescentOptimizer to register PET 
> images. When I monitor the registration progress, I found that the 
> measure value initially goes down during the first couple of iterations, 
> then it just kept increasing for many iterations (the metric was set to 
> be minimized). The increment for each step was not that large though, 
> and it did stop finally. The parameters I  used was:  max step length 
> =20, min step length = 0.01.
> I'm just wondering if this is normal...and if so why is the case? Any 
> help would be appreciated.
> 
> Feng
> 
> 
> _______________________________________________
> Insight-users mailing list
> Insight-users at itk.org
> http://www.itk.org/mailman/listinfo/insight-users
> 
>