@ok1zjf Hello,
I see there are two fields in the dataset - gtscore and gtsummary. Can you explain the difference and significance of these? I see that you have used gtscore in your code while calculating losses. In the readme file, you have written gtscore is the frame-level importance scores and used for regression loss while gtsummary is the ground truth summary which is used for likelihood loss. I couldn't understand this part.
Thank you.
@ok1zjf Hello, I see there are two fields in the dataset -
gtscore
andgtsummary
. Can you explain the difference and significance of these? I see that you have usedgtscore
in your code while calculating losses. In the readme file, you have writtengtscore
is the frame-level importance scores and used for regression loss whilegtsummary
is the ground truth summary which is used for likelihood loss. I couldn't understand this part. Thank you.