Coding Problem in "caption_eval/data/id_to_words.json"

[CollinsWRQ]

Values of key "caption" indicate that they are Unicode utf-8 characters but decoded and saved as ASCII.
I'm not sure whether it's the format required or just an oversight in coding although it may have no affect.

[AIChallenger]

@CollinsWRQ I don't quite understand your concern. We did save captions in utf-8, so regarding ASCII, which part are you referring to? However, it should be noted that utf-8 is required in submission files.