Skip to content
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.

ITERATIVE PROCRUSTES REFINEMENT : TypeError: 'NoneType' object is not subscriptable #162

Open
saharghannay opened this issue Apr 7, 2020 · 1 comment

Comments

@saharghannay
Copy link

Hi

I got this error when training unsupervised multilingual embeddings fr-en using this command line

python unsupervised.py" --exp_path MUSE --dis_most_frequent 0 --n_epochs 5 --cuda 1 --export 1 --src_lang fr --tgt_lang en --emb_dim 100 --max_vocab -1 --src_emb $fr_em --tgt_emb $de_em --refinement 1

Do you have an idea how can I fix this problem please

INFO - 04/06/20 22:18:02 - 0:37:15 - Shrinking the learning rate: 0.02260 -> 0.01130
INFO - 04/06/20 22:18:02 - 0:37:15 - ----> ITERATIVE PROCRUSTES REFINEMENT <----

INFO - 04/06/20 22:18:02 - 0:37:15 - * Reloading the best model from best_mapping.t7 ...
INFO - 04/06/20 22:18:02 - 0:37:15 - Starting refinement iteration 0...
INFO - 04/06/20 22:18:02 - 0:37:15 - Building the train dictionary ...
WARNING - 04/06/20 22:18:03 - 0:37:17 - Empty intersection ...
Traceback (most recent call last):
File "MUSE/unsupervised.py", line 167, in
trainer.procrustes()
File "MUSE/src/trainer.py", line 174, in procrustes
A = self.src_emb.weight.data[self.dico[:, 0]]
TypeError: 'NoneType' object is not subscriptable

@IT-coach-666
Copy link

I also encounter this problem too

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants