Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
fix vocab bug
- Loading branch information
Showing
1 changed file
with
2 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
1 comment
on commit 84dc169
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
FYI, for split=2 and for test-dev2015
- reduced # of questions: 320006 => 320029 (+23)
- total words: 2284474 => 2284620 (+146)
-
of vocab: 14770 (the same, however, the order is shuffled due to introducing few additional questions.)
# of affected questions: 687(train)+142(test) (approx. 0.26%)
@jiasenlu I think this modification is not necessary, because
UNK
is added to a vocabulary set for training.refer https://github.com/VT-vision-lab/VQA_LSTM_CNN/blob/84dc16904065e46f3d42bca3d4b48af224a76572/prepro.py#L70