Thanks for your great work and I have questions about some result.
I downloaded the pretrained model from your google drive and run "evaluate.py".
without multi-scale evaluation implement, the result is quite similar to the paper. however, with it, the result is quite different from the paper.
Did I miss something? if not, could you please explain why the result is different?
Thanks for your great work and I have questions about some result.
I downloaded the pretrained model from your google drive and run "evaluate.py". without multi-scale evaluation implement, the result is quite similar to the paper. however, with it, the result is quite different from the paper. Did I miss something? if not, could you please explain why the result is different?
this is plus v2 model's result(with ms)![image](https://github.com/jamycheung/Trans4PASS/assets/87787966/de4b0db5-26fe-4102-b283-017e3bc78824)
this is original v2 model's result(with ms)![image](https://github.com/jamycheung/Trans4PASS/assets/87787966/7d4186d8-a20b-44b0-9166-66248f6d0fc8)
and here is what I change![image](https://github.com/jamycheung/Trans4PASS/assets/87787966/df4e10c9-fe59-4bbf-aad7-2dde808b7703)