[SciPy-User] Fitting problem using optimize.fmin_slsqp

[Skipper Seabold]

On Thu, May 19, 2011 at 11:50 AM, guillaume gwenael
<guillaume.gwenael at neuf.fr> wrote:
> Do you mean that it is not possible de fit a data array using fmin_slsqp?
> Gwenaël
>

I haven't looked at your code in great detail, but what does your
objective function look like? It looks like you just return an array
of errors. You need some distance measure that returns a scalar. Ie.,
if your objective is to minimize the sum of squared errors, then it
needs to return the sum of squared errors. This is different than say
optimize.leastsq which does the sum and squaring internally.

Skipper