Matthew Aquilina

Results 15 comments of Matthew Aquilina

Hi again @FynnBe, to quickly update, I've managed to validate the model works in DeepImageJ (although that also has its own share of bugs and issues). I'm about to upload...

Great, thanks for highlighting the login issue with the team! Re. the pre-processing, I'm adhering to the spec used for our model [preprint](https://www.biorxiv.org/content/10.1101/2024.09.06.611479v1.abstract) experiments for now but yes percentile normalization...

Looks like the v0.5 version of OutputTensorDescr doesn't take a halo though, right? Link [here](https://bioimage-io.github.io/core-bioimage-io-python/bioimageio/spec/model/v0_5.html#OutputTensorDescr). Also would the `blocksize_parameter` be taken care of by deepimagej automatically or is this only...

Thanks both for the details on the halo syntax. Given that it's not currently accessible to deepimagej, I'll probably circumvent this issue by building in the padding/unpadding into the torchscript...

Actually, it turns out that deepimagej is indeed somehow taking care of padding and unpadding by itself! If I use the below for my inputs: ```python SpaceInputAxis( id=AxisId('x'), size=ParameterizedSize(min=32, step=32),...