Model changes

[b9]

It appears that the default model for GCP Cloud Vision API has changed. Specifically, the current API results lack localized objects that were available previously, say around June 2021. How does the team communicate, if at all, what entities the model supports?

Thanks.

[Sway]

As per the release notes [1], it doesn't seem like there was any change to the default model.

From all of the available models [2], for your use case you can use the object localizer [3].

[1] https://cloud.google.com/vision/docs/release-notes
[2] https://cloud.google.com/vision/docs/reference/rest/v1/Feature#type
[3] https://cloud.google.com/vision/docs/object-localizer