Roland Zimmermann

Thanks for fixing this. Do you mind adding a docstring to the normalize function and adapting the `von_mises_fisher` function as well?

@MiSikora What are your thoughts on this?

Great, thanks for looking into this @MiSikora. I'll implement the necessary changes! @mebarbosa I noticed that you recently (#1862) updated all playback speed resources to ensure they all have the...

@david-gonzalez-a8c Did you have a chance for looking at this PR or can you please send me the templates you created/used? So that we can finalize this PR?

@MiSikora I implemented your suggestions above and think this should complete the PR. Is there anything else that needs to be done before this can get merged? Here is an...

@xuanqing94 Did you run any additional experiments or do you have any explanations for my observations yet? Right now, the results of my experiments look like they contradict the main...

@xuanqing94 Thanks for taking a look into it. I think your argument is only valid for the networks on CIFAR10/ImageNet-143 as for those networks there was this bug in the...

Thanks for bringing this to my attention. I will look into this. If you have any suggestions why this is happening please feel free to share your ideas with me.

Thanks for these observations! I will run some experiments on my own and come back to you afterward.

@bloupo Sorry for my late response, but I was busier than I hoped to be in the past two weeks. Something you could try out is to modify [line 590](https://github.com/FlashTek/keras-utility-layer-collection/blob/master/kulc/attention.py#L590)...