Possible bug in a call?

[tridemax]

trafficstars

https://github.com/kimiyoung/transformer-xl/blob/44781ed21dbaec88b280f74d9ae2877f52b492a5/pytorch/mem_transformer.py#L733

Function signature is: def _update_mems(self, hids, mems, qlen, mlen):

And the call is: new_mems = self._update_mems(hids, mems, mlen, qlen)

mlen and qlen probably misordered in the function call?

[mvedang]

@tridemax was there any improvement in performance after this correction?

[tridemax]

TBH, I didn't tried it in your code, in my TF2.0 implementation I've did it swapped and seems it works. =)

[liuzhejun]

This is indeed a bug, but fortunately it does not affect the training process.