-
Notifications
You must be signed in to change notification settings - Fork 32
Closed
Labels
enhancementNew feature or requestNew feature or request
Description
Great example on using the camera itself to conveniently get training data.
On your example, you mention that "In fact, you can well capture images at the resolution you prefer (up to the RAM limits, of course) and still have space to run FOMO model.".
When doing capture with a modified camera.resolution.face() to say .vga(), the capture interface only seems to be saving the a portion of the streamed image(s). Seems to crop on the top right corner to what I assume is the default resolution of .face()
I couldn't find methods to modify this, so I thought i'd ask you first.
Metadata
Metadata
Assignees
Labels
enhancementNew feature or requestNew feature or request