how to #11863
Labels
api: vision
Issues related to the Cloud Vision API.
priority: p3
Desirable enhancement or fix. May not be included in next release.
type: question
Request for information or clarification. Not an issue.
Dear
Problem:
I'm using google cloud vision for my "Black-box Adversarial Attack" project. When using a function (client.label_detection) to query the model for image annotation, the received response has a few results (labels and scores) which is less than the response from using web demo.
Question:
How can I get a response with more results? How to customise the number of results? I would like to explore different attack settings based on the number of results returned from real-world systems like google cloud vision.
Thanks
The text was updated successfully, but these errors were encountered: