You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I tried modifying the vqa_inference.py file to allow input of multiple images, but the model seems to only recognize the first image. Is there an example of code that supports inputting multiple images?
The text was updated successfully, but these errors were encountered:
Of course, you should try to modify the script by setting the inputs as a loop of image inputs. Then, the model will take all images as inputs one by one.
I tried modifying the
vqa_inference.py
file to allow input of multiple images, but the model seems to only recognize the first image. Is there an example of code that supports inputting multiple images?The text was updated successfully, but these errors were encountered: