fast_abs_rl
fast_abs_rl copied to clipboard
Error while start training abstractor
Hi @ChenRocks , can you please check this issue?
I tried to train your model with my own dataset in Vietnamese. It's OK at step 1 (train_word2vec.py) and step 2 (make_extraction_labels.py)
But when I start training the abstractor, your model return this error
I tried to reproduce that the same step with CNN/DailyMail dataset and the result is the same, it still stuck at step 3 with the same error message as above.
Can you give me some suggestion to overcome that error?
@ithieund Hello! I wonder if you could help me solving this problem.
@ithieund Hello! I wonder if you could help me solving this problem.
Sorry I still don't have any solution for this :(
Find copy_summ.py in ./models/. Change source in "source=score.contiguous().view(beam*batch, -1) * copy_prob" and "source=score * copy_prob" to src will work.