Train custom machine learning models
Cloud AutoML is a suite of machine learning products that enables developers with limited machine learning expertise to train high-quality models specific to their business needs. It relies on Google’s state-of-the-art transfer learning and neural architecture search technology.
Cloud AutoML leverages more than 10 years of proprietary Google Research technology to help your machine learning models achieve faster performance and more accurate predictions.
Get up and running fast
Use Cloud AutoML’s simple graphical user interface to train, evaluate, improve, and deploy models based on your data. You’re only a few minutes away from your own custom machine learning model.
Generate high-quality training data
Google’s human labeling service can put a team of people to work annotating or cleaning your labels to make sure your models are being trained on high-quality data.
Create your own custom machine learning models with an easy-to-use graphical interface.
Derive insights from images in the cloud or at the edge.Learn more
AutoML Video Intelligence
Enable powerful content discovery and engaging video experiences.Learn more
AutoML Natural Language
Reveal the structure and meaning of text through machine learning.Learn more
Dynamically detect and translate between languages.Learn more
Automatically build and deploy state-of-the-art machine learning models on structured data.Learn more
Cloud AutoML’s technology is helping us build vision models to annotate our products with Disney characters, product categories, and colors. These annotations are being integrated into our search engine to enhance the impact on Guest experience through more relevant search results, expedited discovery, and product recommendations on shopDisney.— Mike White, CTO, SVP, Disney Consumer Products and Interactive Media
How AutoML works
Cloud AutoML features
Train custom machine learning models that are specific to your business needs, with minimum effort and machine learning expertise.
Powered by Google’s AutoML and transfer learning
Leverages Google state-of-the-art AutoML and transfer learning technology to produce high-quality models.
Cloud AutoML is fully integrated with other Google Cloud services, giving you a consistent way to access the entire Google Cloud service line, including storing your training data in Cloud Storage. To generate a prediction on your trained model, simply use the existing Vision API by adding a parameter for your custom model or use Cloud ML Engine’s online prediction service.
Integration with data labeling service.
If you have images but no labels yet, an in-house Google team will review your custom instructions and classify your images accordingly. You’ll get high-quality training data while your data remains private. You can also use the human-labeled data seamlessly to train a custom model. Available for AutoML Vision only.
Start training high-quality custom ML models.
Access how-to guides, quickstarts, and more.
This product is in beta. For more information on our product launch stages, see here.