-
-
Notifications
You must be signed in to change notification settings - Fork 1.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Examples/tutorials of Adaptive Metropolis for images using PyMC #653
Comments
The closest I know of is here: http://nbviewer.ipython.org/github/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers/blob/master/Chapter5_LossFunctions/LossFunctions.ipynb (see I think the question is a big too vague. What kind of example are you looking for specifically? Object recognition, etc? |
I see. What about finding the peak on this simulated array?
|
In that case it seems like you are trying to estimate a 2-D uniform distribution with gaussian noise. You'll have to translate this into an actual model but this would be one idea: lower_x ~ DiscreteUniform(0, 20) data ~ Normal(mu=means, sd=noise) |
You can add a potential to enforce lower_x < upper_x and the same for y. |
Thank you for the help! I've attempted to follow your suggestion, I wrote this:
But it is clearly wrong, there is not model convergence (xs' and ys' traces are steady). Incidentally, could you please answer the question also on StackOverflow? |
I asked this question on Stackoverflow, but without any luck at this time:
http://stackoverflow.com/questions/27261233/examples-tutorials-of-adaptive-metropolis-for-images-using-pymc
What's wrong with the question? Too generic?
If not specific for image processing, can somebody help me to find a minimal code example using PyMC and data stored on numpy 2/3d arrays for Bayesian inference?
The text was updated successfully, but these errors were encountered: