aliftadvantage
aliftadvantage
Is there any update on this? Has there been any announcement?
Wanted to follow up on this, I think the default setting for BLIP is 20 tokens. Maybe we could add a parameter to allow us to adjust this?
Going on two years here, but this would be awesome! The important thing here is that downloading weights and compiling would all happen at the build stage. As opposed to...
This looks really cool. What would be the benefits of having it in KerasCV vs AutoML? AutoML implementation: https://github.com/google/automl/tree/master/efficientdet