Nick Weir

@avanetten you have some code for converting to TFrecords that could potentially be popped in here, right?

@jacquesmats, See #212 for a solution to the second problem. Without seeing the image file you're passing in, I can't do much to help with the first. I assume you're...

Thanks @jacquesmats for the clarification and glad it worked. I'm going to re-name the issue and flag it to help with tracking. My guess is that the issue is related...

FYI: I'm going to start implementing this. I'll try to write guidelines as I do so for future logging. Resources that I'm using to guide implementation: https://docs.python-guide.org/writing/logging/ Will get the...

Thanks @EugeneDG! Some of these are indeed broken, other places we just need to point to a more informative page when the content hasn't been created yet.

Hi @mlubej! Thanks for bringing this up. I agree that using the version from `tqdm.auto` is better. If you have the time to make those changes and put in a...

Worth noting, though, that at least in some Jupyter environments, `from tqdm.auto import tqdm` doesn't really solve the problem. I was just trying that out in a Jupyterlab notebook I'm...

Yeah...that makes sense! Thanks.

Hey @rbavery. I think mean filling for images themselves is a valid option, but less so for labels. The approach described in `2` above is for the training objective masks...

I don't think this actually fully solves the intention of this request - specifically, to find a way to mask out areas from contributing to the loss function. So I'll...