[GitHub] [incubator-mxnet] xidulu edited a comment on issue #19722: [RFC + BUG?] Implementation of Categorical distribution

[GitBox <gi...@apache.org>]

xidulu edited a comment on issue #19722:
URL: https://github.com/apache/incubator-mxnet/issues/19722#issuecomment-753294152


   Hi @dibgerge 
   The reason "num_events" is required is that we cannot call `logit.shape` or `prob.shape` in the symbolic mode, as you can see, TF would use a very complicated subroutine to get num_events in the symbol mode: https://github.com/tensorflow/probability/blob/v0.11.1/tensorflow_probability/python/distributions/categorical.py#L352
   while torch does not have such issue : https://github.com/pytorch/pytorch/blob/master/torch/distributions/categorical.py#L57
   
   You are also right about the `logit` issue, that could be a **bug**. But MXNet currently does not have a logsumexp Op, a relative Op would be logaddexp, which is still not merged yet: https://github.com/apache/incubator-mxnet/pull/15857


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@mxnet.apache.org
For additional commands, e-mail: issues-help@mxnet.apache.org