How to merge results of Mask2Former from multiple image patches during testing? #9799
Unanswered
Amr-Mustafa
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi all! So I trained Mask2Former on 912x912 image patches since the input images are very large. When doing inference, I want to also split the input image into similar non-overlapping patches and perform inference on each patch independently. However, I want to combine their results in the end into a single output image. Did anyone come across something similar?
Beta Was this translation helpful? Give feedback.
All reactions