James Dolezal

I've just added a possible solution for attention-based MIL - give it a try and let me know if it works!

Glad to hear it! Re: dependencies - as you are aware, Slideflow is seeking to support a diverse set of deep learning tasks (segmentation, image generation, self-supervised learning, classification) and...

[Slideflow Studio](http://github.com/jamesdolezal/slideflow) is a user interface for deploying deep learning models for digital pathology research applications. Dear Imgui (and the python wrapper, [pyimgui](https://github.com/pyimgui/pyimgui)) were essential in making this a success....

I can reproduce the same issue, using the above code snippet, on Ubuntu 22.04 & Python 3.9.13. Not sure if the problem is glibc - my version is 2.35.

This is the GDB stacktrace, if it's helpful: ``` (gdb) info frame Stack level 3, frame at 0x7ffff5b5c2f0: rip = 0x7ffff62e9e6a in DeleteChild(mvAppItem*, unsigned long long); saved rip = 0x7ffff62ea074...

This is a great idea! We'll need to put some time into thinking about how to integrate this option into a UI in a way that would be intuitive. But...

Thanks for the PR - this seems like a good idea. I'll run some tests to ensure nothing breaks, and if all is good, we should do this for the...

Just a quick update - I did have some issues with this multi-stage approach during initial testing, which is why I haven't been able to merge quite yet. I'll keep...

Thanks for this suggestion. At present, Slideflow could be used for image processing and preparation of feature bags (in PyTorch format) for external, customized MIL training loops like WENO. I...

Does your workflow require that a new project be created from the same script that is executing the feature bag generation? Typically, once a project is created, you should not...