Open ezyang opened 7 years ago
I originally thought that no one would actually do this, but I was wrong! In bnlstm, https://github.com/pytorch/benchmark/blob/master/benchmarks/models/bnlstm.py an integer "time" is passed in to SeparatedBatchNorm1d, which is used to determine which running_mean and running_var is used.
running_mean
running_var
If there are many other incidences of this, we may have to support this.
If the PyTorch API lets someone do something, they'll do it... but yeah recurrent batchnorm is the only situation I know of where you basically can't refactor such an auxiliary input out
I originally thought that no one would actually do this, but I was wrong! In bnlstm, https://github.com/pytorch/benchmark/blob/master/benchmarks/models/bnlstm.py an integer "time" is passed in to SeparatedBatchNorm1d, which is used to determine which
running_mean
andrunning_var
is used.If there are many other incidences of this, we may have to support this.