Video-LLaMA icon indicating copy to clipboard operation
Video-LLaMA copied to clipboard

Published 20 hours ago • verified publisher icon DAMO-NLP-SG

What is the input sample of the forward function in videollama

Open llx-08 opened this issue 11 months ago • 1 comments

Hi, I'm wondering what is the input sample of the forward function in videollama.py.

1709872064572

It seems like an dict() which contains image, text_input as its keys, but I can't find any usage as example. Besides, I check the inference process in demo_audiovideo.py, it's different with the forward process. Can you provide some example to use the forward function in videollama? Thank you very much!

llx-08 avatar Mar 08 '24 04:03 llx-08

I am also finding this solution.!

EQ3000 avatar Apr 28 '24 04:04 EQ3000