Closed davebulaval closed 5 months ago
The problem is the breaking change with the change of n_out
in the TransformerEmbedding
from n_feat_embed
to n_plm_embed.
Thus, the pre-trained model does not set up this value correctly and the n_plm_embed = 0
, thus the projection layer is (768, 768)
instead of (768, n_feat_embed)
This issue is stale because it has been open for 30 days with no activity.
This issue was closed because it has been inactive for 7 days since being marked as stale.
Hi,
In this part of the code https://github.com/yzhangcs/parser/blob/bebdd350e034c517cd5b71185e056503290164fa/supar/model.py#L93C2-L116C60, when you set "bert" as the encoder, it does not init the
word_embed
attribute. Thus, it will fail at the load_pre_trained. And I cannot find a way to skip this.