GL-RG
GL-RG copied to clipboard
Hi! Why the shape of msvd_train_evalscores.pkl is [1200,17]?
Thank you for your great work! There are different numbers of captions for every video in MSVD
dataset, such as 29, 42……But I found that the shape of msvd_train_evalscores.pkl is [1200,17], why there are only 17 captions' scores for every video in training set?