What is the reason of rnn's batch_first parameter is set False as default?

nlp
#1

Hello every one. I’m beginner at nlp. i’m learning about how use nn.RNN with pytorch docs.

before start, i’m not good at english grammar XD )

in docs, nn.RNN’s parameter ‘batch_first’ is False in default.

it seems that people use batch_first == False ususally. ( i saw a lot of input datasets are same like that not only at simple nlp model but also at complicated nlp model(e.g bert) )

Can you let me know why people uses dataset’s shape as T x B x * (T is max length) ??

is there any advantages when i set dataset’s shape like that?

Thank you!!

#2

There’s no strict advantages or disadvantages. It could be that because, in an RNN, we’re iterating over the sequence dimension (we take timestep-0, then timestep-1, etc.) so it makes “sense” to have that dimension first. But it doesn’t really make a difference.

I would suggest just going with the default option only because it’s default.

2 Likes
#3

Thank you for your helpful answer :smiley: