Giters

zengyan-97 / X-VLM

X-VLM: Multi-Grained Vision Language Pre-Training (ICML 2022)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

apply an entire BERT as text encoder

lxianl455 opened this issue · comments

commented

Can I apply an entire BERT as text encoder ? Not just 6 layer.
What should I do to apply an entire BERT as text encoder ? And another BERT as the cross modal encoder?

commented

Hi,

it's OK. I also used 12+6 architecture in X^2-VLM.