Cloud AutoML Vision Object Detection documentation

Beta Features Overview

Cloud AutoML Vision Object Detection enables developers to train custom machine learning models that are capable of detecting individual objects in a given image along with its bounding box and label.

The Cloud AutoML Vision Object Detection Beta release includes the following features:

  • Object localization - Detects multiple objects in an image and provides information about the object and where the object was found in the image.

  • API/UI - Provides an API and custom user interface for importing your dataset from a Google Cloud Storage hosted CSV file and training images, for adding and removing annotations from imported images, for training and reviewing model evaluation metrics, and for using your model with online prediction.

salad test image
Image credit: H. Michael Karshis, (UI annotations added, CC BY 2.0).

Terms of Service

Product usage is under Google Cloud's Terms and Conditions and customer information will be used in accordance with Google's Privacy Policy.

Оцените, насколько информация на этой странице была вам полезна:

Оставить отзыв о...

Текущей странице
Cloud AutoML Vision Object Detection