You have to try every possible solution to get the most optimal result. Let’s say that the function to minimize is arbitrarily complex (nonlinear), this is a complicated problem in general. Message: 'Optimization terminated successfully.' Res = minimize( doSingleIteration, parameters, method='Nelder-Mead',options= <- input to my algorithm rounded and made intġ20 <- output of the function I am trying to minimize # return the difference between my value and the truth value Does anyone know how to tell scipy to use a specific step size for each parameter? Is there some way I can roll my own gradient function? Is there a scipy flag that could help me out? I am aware that this could be done with a simple parameter sweep, but I would eventually like to apply this code too much larger sets of parameters. Roughly one parameter is a window size in pixels and the other parameter is a threshold (a value from 0-255).įor what it is worth I am using a fresh build of scipy from the git repo. the value must be odd, if it isn't the thing I am trying to optimize will convert it to an odd number). The current set of parameters are both integers and one has a step size of one and the other has a step size of two (i.e. I got the code all set up but it seems that the minimize function really wants to use floating-point values with a step size that is less than one. The Nelder-Mead implementation in SciPy seemed like a good fit. Right now I only want to tune-up two parameters but the number of parameters might eventually grow so I would like to use a technique that can do high-dimensional gradient searches.
I have a computer vision algorithm I want to tune up using.
0 kommentar(er)
