Dominik Kutra

Hey @tboo, thank you very much for following up and adding additional information! The Pixel + Object Classification workflow is not really intended for production use - it's mainly there...

Hey @chaytanc, sorry you ran into this issue, but it looks like you're already on a good path to its resolution. The prediction files, I assume, are stored at a...

Thanks for providing the concise example - very easy to reproduce. The root cause seems to be ilastik/lazyflow creating worker threads once imported. These will not be available to the...

I'd like to keep it open until we find a user friendly solution to this. I've to admit that I haven't thought about this before - so it's great that...

Hello @AnnCloos, I've overlooked this issue in my feed - apologies for the delayed response. While the _contour export_ is, unfortunately known to be broken, you also experience not being...

Seems the reason is that this shortcut is not registered at all :/

of course. In the meantime, I use the shortcut `i` a lot (to toggle between whatever you are looking at and raw-data-only display).

So I did some benchmarking on a machine with `20` cores, `40` threads. Task was pixel classification on some cremi sample dataset. In addition to varying `n_threads`, I also varied...

Hi @sitesite53, sorry that you ran into this problem! Your data is quite big - how much RAM do you have available? (The memory error is raised once more memory...

Hello @sitesite53, It is hard to answer the question without seeing any data. Also note, that for these kinds of analysis advice questions [forum.image.sc](https://forum.image.sc/tag/ilastik) is a better place - there...