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 am currently working with SAHI’s get_sliced_prediction function and I want to apply padding to the slices generated during inference. While researching, I came across references to a parameter named context_amount that is supposed to control padding around the slices.
However, after inspecting the function’s parameters, I could not find context_amount listed. I have a few questions:
Does SAHI currently support slice padding through any parameter, such as context_amount?
If yes, how should it be used effectively to include context around slice edges?
If not, are there any recommended workarounds to simulate padding for better detection accuracy near slice borders?
Any detailed explanation, example, or guidance would be highly appreciated.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Hi,
I am currently working with SAHI’s get_sliced_prediction function and I want to apply padding to the slices generated during inference. While researching, I came across references to a parameter named context_amount that is supposed to control padding around the slices.
However, after inspecting the function’s parameters, I could not find context_amount listed. I have a few questions:
Does SAHI currently support slice padding through any parameter, such as context_amount?
If yes, how should it be used effectively to include context around slice edges?
If not, are there any recommended workarounds to simulate padding for better detection accuracy near slice borders?
Any detailed explanation, example, or guidance would be highly appreciated.
Thank you!
Beta Was this translation helpful? Give feedback.
All reactions