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
It would be great if when picking model training options like Max Stride and Input Scaling, we could flip through a random subset of example frames rather than seeing just a single frame. This would help when evaluating how the blue box maps onto frames in videos where animals move toward and away from the camera and change size appreciably.
This discussion was converted from issue #664 on September 11, 2023 22:47.
Heading
Bold
Italic
Quote
Code
Link
Numbered list
Unordered list
Task list
Attach files
Mention
Reference
Menu
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
-
Hello,
It would be great if when picking model training options like Max Stride and Input Scaling, we could flip through a random subset of example frames rather than seeing just a single frame. This would help when evaluating how the blue box maps onto frames in videos where animals move toward and away from the camera and change size appreciably.
Thanks!
Beta Was this translation helpful? Give feedback.
All reactions