salesforce / BLIP

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
BSD 3-Clause "New" or "Revised" License
4.84k stars 646 forks source link

what is mean of 'question_states += [question_output.last_hidden_state[b]]*n' #178

Open ericosmic opened 1 year ago

ericosmic commented 1 year ago

I don't understand a code snippet in blip_vqa.py line61-67:

image

How to understand of this function? Anyone help?