Karol Żak

Hi @dpoiesz ! The answer to your problem is in this single line: ``` ValueError: Shapes (None, 256, 256, 1) and (None, 68, 68, 1) are not compatible ```` I...

512x512 is now both your input size and output mask size, right? That's incorrect for vanilla unet. `valid` padding is losing border pixels information on each consecutive conv layer so...

Hi @maxpv Good catch! Seems to be a mistake indeed.

Hi @sivaramakrishnan-rajaraman Unfortunately these utils lack any tests or whatsoever and they were develop in a rush and designed only for single layer masks. Don't have any quick fix for...

Hi @martinkozle ! Thanks for sharing your issue. Looking back I agree that putting that hardcoded `(1,1)` value for `group_size_range` wasn't the best practice but I can definitely share some...

Hi @iperez-pasiona Have you tried going through the logs and checking what is the error message? It would strongly help to identify the cause. You should be able to find...

> Did you figure why it's occurring? Did you decided to blur all the masks before using them in the model? Yes, bluring seems to help for my inputs, so...

> @karolzak thanks for your good work, I want to fine-tune the model. But I could not find how to do it? could you please let me know how to...

> @karolzak thanks a lot for your helpful response. In the Readme file, it says to provide the below directories, how many images did you put in these folders as...

Hi @nesaboz , There's no way to hide it as of right now, but this can be easily added as and argument. Hmm, I can imagine a scenario where this...