core-bioimage-io-python
core-bioimage-io-python copied to clipboard
Python libraries for loading, running and packaging bioimage.io models
- [ ] the citation doi `doi:10.1002/xyzacab123` is not valid _Originally posted by @FynnBe in https://github.com/bioimage-io/collection-bioimage-io/issues/510#issuecomment-1331932168_ This should be picked up by the dynamic url validation. Maybe this is actually...
We should improve the TF Model Adapter to be more robust. I can't improve this right now, but here are some notes from looking into it briefly, if someone else...
I have a lot of uncertainty in this process. It would be nice if I can debug the various steps. I have a model, I load images as [t, c,...
Discussion from the BMZ meeting, proposed by @ivan-ea Would be nice to support adding multiple weights in the build_model function. cc @constantinpape @FynnBe
Currently during prediction overlapping parts of tiles are just cropped. Would be useful to have different modes for dealing with it, for example, add also averaging and averaging based on...
Hello. It is hard to understand from code, what is the difference between `predict_with_tiling` and `predict_with_padding` and what parameters mean. From searching the repo, trying things and talking to Constantine...
For the napari plugin, I noticed that the downloading can take more than 10 minutes for some models, during this time, it would greatly improve the user experience if we...
`export_resource_package` can take a long time, the function itself doesn't give any feedback. Deeper in the callstack there might be progress printed to the command line, but that is not...
Generally useful to support inference on a triton server, and in particular for more robust prediction implementation in the BioEngine, see https://github.com/bioimage-io/bioimage.io/issues/290#issuecomment-1140471598.
Environment set up for`Test and Deploy bioimageio.core / test-base-bioimage-spec-tf-legacy (3.7)` fails with: ``` Looking for: ['black', 'bioimageio.spec', 'conda-build', "h5py[version='>=2.10,=3.7,1.14,