Jeshua Lacock
Jeshua Lacock
I don't know - sounds like they aren't very sharing of the details. ;) I mean - could they be any more vague?
It was just a gut feeling. That said - there are practically an infinite number of variations possible.
I think the scaling is better fit for the Dreamscope examples - but other than that personally I think your CNNMRF results are much better.
Here's another example of "garbage". 
Ubuntu.
I appear to be having the same issue #992 I was able to work around the bug by using MultiArray input and flexible shape image output (as you mention). I...
You're welcome! Possibly. Please see the end of this thread for the solution: https://github.com/hollance/CoreMLHelpers/issues/5#issuecomment-726021906
I'm trying to wrap up development of an update that I've spent 2 years working on. Is this glaring bug ever going to be addressed? Otherwise I am facing shipping...
Hi Mstronach, you're quite welcome. Yes, it appears to be a duplicate. I hadn't noticed the double-post before. It must have gotten posted twice by accident.
My workaround of using a flexible-shape multi-array input to get flexible shape output no longer works with 5.0b1. The flexible input array works, but, the output is the fixed image...