[Insight-users] Access to Jacobian of LM Optimizer

[Luis Ibanez]

Hi Mark,


You are right,

Unfortunately the get_JtJ() is not implemented in the
vxl beta version. It seems too risky to try to get it
from the cvs version.

Could you describe in more detail your final goal ?

Maybe there is an alternative way to get there.

For example, if you are using the LM optimizer from
the ITK Optimizer adaptor, you are now providing an
ITK multivalued cost function to the optimizer.

It may be possible to get the Jacobian directly from
the function, instead of querying the optimizer....


   Luis


===========================================



Mark Hastenteufel wrote:

> Hi Louis,
> 
> You're right. One can compute the singular values
> from JtJ. But the version of vnl you use currently
> does not implement the get_JtJ() method of the 
> levenberg-marquardt optimizer. In the 
> current cvs snapshot of vxl/vnl this method is implemented.
> Are you plan to integrate the current vxl/vnl version
> into ITK in next time?
> 
> 
> Thanks,
> 
> Mark
> 
> 
> 
>