Mario Klingemann

Something I am currently doing for testing things quickly is to reduce ndf and ngf from 64 to 32. This allows me to increase the batch size and the visible...

So if I understand it correctly you are trying to sharpen details? In that case I would create lots of small tiles that show just parts of the huge image...

It might be the case that one of the libraries used has become stricter since I released the code and does not automatically convert floats to ints. I remember having...

Ah okay - so yes, this is written for Python 2.7 and I have not made sure that it also works with Python 3+

Unfortunately I don't speak MATLAB but I am pretty sure it is possible to port it - the code just uses basic operations and no special native codes or additional...

https://github.com/Quasimondo/QuasimondoJS/blob/master/blur/stackblur.pdf

Thanks for looking into this! I'll try to patch my code accordingly. I did not run into any unusual issues with the mask apart from the already mentioned general incompatibilities...

Thanks! The only problem I have with this change is that it will probably break the demo notebooks since they expect only two arguments being returned..

Yeah the blockiness is the result of the way Rasterfairy subdivides the cloud which is purely based on vertical and horizontal splits. This is fast but can lead to sub-optimal...

That is strange since as you can see in the rasterfairy/rasterfairy.py code there is a method with that name. Sounds like some import issue to me. Are you using Python...