Jennifer-6

object tags

2

Is word embedding of object tags the same embedding matrix as word embedding of caption

datasets/coco_caption/test.yaml

1

can't find datasets/coco_caption/test.yaml

what is the input of nocaps inference? the image or the image feature throngthout vinvl?

where is the nocaps task trained model?

train time

1

How long does it take to train the network?

how to visualize the Saliency Maps?