You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Jun 10, 2021. It is now read-only.
Hello, we have trained a bidirectional rnn encoder decoder (default OpenNMT-lua settings) and successfully released the model and tested using this repository. However, when we are working through the paper (http://aclweb.org/anthology/W18-2715) and try to replicate the distill-tiny model with a GRU encoder with 2-layers on the encoder but only 1-layer on the decoder, we run into the issue that the released model doesn't translate anything using the GPU (--cuda). When I run on the CPU, I get the following error:
Intel MKL ERROR: Parameter 10 was incorrect on entry to SGEMM .
The model can accurately translate using the lua code so we know it isn't any issue with the model but must be something incompatible when we try to release to CTranslate. Here is the full configuration used to train:
Thank you for the response. Does the "last" bridge support a different number of encoder/decoder layers (e.g. 2-layer encoder and 1-layer decoder)? I know "copy" doesn't work when the number of layers are different.
Hello, we have trained a bidirectional rnn encoder decoder (default OpenNMT-lua settings) and successfully released the model and tested using this repository. However, when we are working through the paper (http://aclweb.org/anthology/W18-2715) and try to replicate the
distill-tiny
model with a GRU encoder with 2-layers on the encoder but only 1-layer on the decoder, we run into the issue that the released model doesn't translate anything using the GPU (--cuda
). When I run on the CPU, I get the following error:The model can accurately translate using the lua code so we know it isn't any issue with the model but must be something incompatible when we try to release to CTranslate. Here is the full configuration used to train:
Does CTranslate support
GRU
as arnn_type
and does it supportdense
as an option for-bridge
?The text was updated successfully, but these errors were encountered: