how to do batch prediction on feature extraction task?

[Tangnameless]

from demo.ipynb, i see

multimodal_feature = model(image, caption, mode='multimodal')[0,0]
image_feature = model(image, caption, mode='image')[0,0]
text_feature = model(image, caption, mode='text')[0,0]

can i make batch prediction?

[LiJunnan1992]

Yes you can.