how do vision transformers deal with input images with different sizes?

Asked Oct 12 '21 at 12:07

Active Jun 15 '23 at 12:37

Viewed 241 times

I want to train a vision transformer with progressive learning which is used in EffientNetV2. Is there any way to do this in a transformer model?

edited Jun 15 '23 at 12:37

Preetom Saha Arko

asked Oct 12 '21 at 12:07

LSC

Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. – Community Oct 14 '21 at 15:03

0 Answers0