search

QUVA-Lab / e2cnn

E(2)-Equivariant CNNs Library for Pytorch
https://quva-lab.github.io/e2cnn/
Other
596 stars 75 forks source link

Difference between trivial output type and regular output type with group pooling #73

Closed SpikeRXWong closed 1 year ago

SpikeRXWong commented 1 year ago

Hello, I have a question about the trivial output and regular output followed by group pooling?

Gabri95 commented 1 year ago

hi @SpikeRXWong

I am not sure I fully understand your question.

Typically, one uses GroupPooling to turn a feature with regular type into a feature with trivial type. What do you mean by "trivial output type with group pooling" ?

By the way, note that this is an older version of the library. I'd recommend you to move to the new escnn library which extends e2cnn and which I am more actively maintaining.

Best, Gabriele