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
After peaking under the hood looks like the coordinates are based on a 360x360 image reshape. After reshaping the mask to my image shape I was able to get a reasonable projection.
I ran the sample docker inference and obtained the mask below:
It appears there's a scale transform that I am missing. What post processing is needed to get the image to the right shape?
The text was updated successfully, but these errors were encountered: