Gabriele Cesa

Oh damn, I never tried combining escnn with multiprocessing :/ What do you think is the cause of this? Is it because some representations are not picklable? I need to...

Hi @dc250601 Unfortunately, this can happen for wide models. This is due to the slow computation of the variance needed for He weight initialization [here](https://quva-lab.github.io/escnn/_modules/escnn/nn/init.html#generalized_he_init). To speed this up, these...

Hi @Ale9806 Thanks for the question! You are right, I will try to prepare a simple example in the next days :) Anyways, R3Conv works exactly like R2Conv, so you...

Sorry for the delay on this, but I am a bit busy in this month so I have not finished preparing these examples yet. I will try to complete this...

hi @psteinb , Sorry for the confusion but, unfortunately, the term *induced representation* is used in two contexts in practice. Given two groups `H < G` (H is a subgroup...

I keep this issue open in case you want to discuss induced representations further. I have finally included an example of 3D equivariant CNN, I'm sorry for the delay but...

hi @Ale9806 Are you sure you are using the latest version of the library? SO3 does have that method as you can see [here](https://github.com/QUVA-Lab/escnn/blob/master/escnn/group/groups/so3group.py#L796) Could you maybe check `escnn.__version__`? Best,...

Maybe it's simpler to explain it via an example. Say we build a G=SO(3) equivariant MLP using Fourier-based pointwise non-linearities. If we use the FourierELU non-linearity, it assumes we employ...

Hi @emilemathieu I am sorry for the late reply, but I was on vacation in the last couple of weeks. I am not currently planning to support other frameworks like...

Hi @psteinb Thanks for pointing this out! Do you have any recommendations on how to deal with this? I did not want to use a *randomly* generated image with numpy...