Facial free image info remember
This model is great for anyone building an app that monitors or detects human activity. Simply pass in an image input with a publicly accessible URL or by directly sending image bytes. The Predict API returns probability scores on the likelihood that the media contains human faces. If human faces are detected, the model will also return the coordinate locations of those faces with a bounding box. They are specified as float values between 0 and 1, relative to the image size; the top-left coordinate of the image is 0. If the original image size is width, height , then the box above corresponds to the box with top-left corner at x, 83 y and bottom-right corner at x, y.