Mario Klingemann

Results 84 comments of Mario Klingemann

@rolux Yes, I did some more changes to the training method and also trained for longer. The major change is probably that I also mix W's resulting from previous descends...

Yes, I can confirm that this fix does not work as intended: Here is an example where the camera is rotated 90° when using the fix, but correctly pointing up...

Thanks for the quick response! I am looking at the source right now and will see if I can patch it to my needs. I am thinking of adding one...

I think this might do for my purposes: ``` def build_sknw(ske, multi=False): buf = buffer(ske) nbs = neighbors(buf.shape) acc = np.cumprod((1,)+buf.shape[::-1][:-1])[::-1] mark(buf, nbs) pts = np.array(np.where(buf.ravel()==2))[0] if len(pts)==0 and np.sum(ske)>0:...

Oh yes - thanks for checking the code and finding the issues with it - I just needed it for a very simple example so I did miss the other...

Perfect - looks like it works as intended. Thanks for the quick fix! ![image](https://user-images.githubusercontent.com/182098/96249474-84667c80-0fad-11eb-8998-9b994e4d3741.png)

Not sure if you saw that this project is 7 years old? So yes, back then I had a working prototype, but by now it's disassembled. I recommend you to...

Same here - keeps happening since a few days. One thing I notice is that some of my primitives with "increment" in control_after_generate stop incrementing.

Actually I just realized that in my case this is probably caused by a primitive "INT" being limited to a max of 2048 (since that was the maximum returned by...

@nikjetchev - looks like you checked out the master branch instead of the continuous-masking one - I made the same mistake.