Tivadar Danka

That is a good idea! I am going to take a shot this. I don't promise to do this ASAP since I am extremely busy with other work, but I'll...

Hi! Sure, this would be awesome! Open the PR and I'll take a look at it. (Just a disclaimer, I am quite busy with other projects at this time, so...

Hi! No, unfortunately not. Due to other projects and lack of time, I abandoned the implementation of major features such as this.

Hi! Can you give a code snippet with the error log? I am not exactly sure what you refer to, but I would be happy to take a closer look.

I have created the ```feature/bayesianDL``` branch for this purpose. I think that the acquisition functions should be implemented in the ```modAL.bayesianDL``` module. I am not sure that we can implement...

You get the error during the initialization? From the error details, it seems like you have the error after you first try to call `learner.fit()` or `learner.teach()`, because it refers...

Thanks for the clarification! Which Keras version you are running? (You can find this by for example `pip freeze | grep keras`.) It seems to me that the problem is...

Sorry for the late answer, I was extremely busy. I was checking out an earlier version of Keras which didn't contain this restriction, so I would suggest the most recent...

Hi! Yes, it can, if it follows the scikit-learn API: [https://modal-python.readthedocs.io/en/latest/content/overview/Extending-modAL.html#Using-your-custom-estimators](https://modal-python.readthedocs.io/en/latest/content/overview/Extending-modAL.html#Using-your-custom-estimators)

Hi! To use the `Committee`, you have to provide a list of active learners explicitly, for example: ```python from modAL.models import Committee from modAL.disagreement import vote_entropy_sampling # a list of...