Closed sharontaozi closed 4 years ago
During training, we sample one description from the collection for each forward pass.
@sharontaozi, closing for now (but feel free to re-open if it's still unclear).
The article mentions that "where they randomly chose 5 ground-truth sentences per video. We use the same setting when we compare with that approach".Does the training set, validation set and test set all take 5 sentences at random? Not all sentences are used in training set, validation set and test set?
In dataset MSVD, the number of text descriptions to each video is different. How do you deal with this problem in your experiment?