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
{{ message }}
This repository has been archived by the owner on Dec 21, 2023. It is now read-only.
The feature extractor used image classifier and image similarity sets the batch size to 512 and we should expose that parameter all the way up to the image classifier and image similarity.
The text was updated successfully, but these errors were encountered:
If we do this, it would be good to expose this for object detection too to allow low-memory GPUs. However, it is harder since it doesn't use a stopping criterion based on a validation set and instead a heuristic to set the number of iterations. This heuristic would get more complicated.
The feature extractor used image classifier and image similarity sets the batch size to 512 and we should expose that parameter all the way up to the image classifier and image similarity.
The text was updated successfully, but these errors were encountered: