You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
My training process has just stuck in Meteor function "compute_score",
leaving a message "computing METEOR score...".
Not sure if anyone encountered this issue before?
I'm using python3 to run the training, after 2to3 all files including coco_caption.
I also modified some codes to solve exception 'TypeError: a bytes-like object is required, not 'str'" by the following codes: sentences_bytes = bytes(sentences, 'utf-8')
Or can I simply disable the option '--language_eval' ?
Thanks!
The text was updated successfully, but these errors were encountered:
Hi TAs:
Should out report contain language_eval results?
If no, I think we can set "--language_eval 0" for both train.py & eval.py just mentioned from Tingchu's comment.
Hi TAs,
My training process has just stuck in Meteor function "compute_score",
leaving a message "computing METEOR score...".
Not sure if anyone encountered this issue before?
I'm using python3 to run the training, after 2to3 all files including coco_caption.
I also modified some codes to solve exception 'TypeError: a bytes-like object is required, not 'str'" by the following codes:
sentences_bytes = bytes(sentences, 'utf-8')
Or can I simply disable the option '--language_eval' ?
Thanks!
The text was updated successfully, but these errors were encountered: