allenai / allennlp

An open-source NLP research library, built on PyTorch.

Home Page:http://www.allennlp.org

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Mismatched found in ensure_batch_predictions_are_consistent. Is is important?

huhk-sysu opened this issue · comments

Hi, I'm using allennlp.common.testing.model_test_case to test my model, and it reports lots of mismatched, though the value seems small.
image

  1. I'm not sure if it is important to me. Do I need to fix it?
  2. If so, what would be the cause and how can I fix it?

ps: I notice that my prediction (which are calculated based on the logits) are the same.

This issue is being closed due to lack of activity. If you think it still needs to be addressed, please comment on this thread 👇