This page describes the main features of Deep Learning VMand Deep Learning Containers, andhelps you understand how you might use these products withVertex AI.

Deep Learning VM

Overview

Deep Learning VM Images is a set ofvirtual machine images optimized for data science and machinelearning tasks. All images come with key ML frameworks and toolspre-installed. You can use them out of the box on instances withGPUs to accelerate your data processing tasks.

Deep Learning VM images are available to support many combinationsof framework and processor. There are currently images supportingTensorFlow Enterprise,TensorFlow, PyTorch, and generic high-performance computing,with versions for both CPU-only and GPU-enabled workflows.

To see a list of frameworks available, seeChoosing animage.

To learn more, see theDeep Learning VMdocumentation.

Using Deep Learning VM

You can use a Deep Learning VM instance as a partof your work in Vertex AI. For example, you candevelop an application to run on a Deep Learning VMinstance to take advantage of its optimized data-processing capability.Or use a Deep Learning VM instanceas a development environment for a self-managed distributed trainingsystem.

You can create Deep Learning VM instances on theDeep Learning VM Cloud Marketplacepage in the Google Cloud console.

Go to the Deep Learning VM Cloud Marketplacepage

Deep Learning Containers

Overview

Deep Learning Containers are a set of Docker containerswith key data science frameworks, libraries, and tools pre-installed.These containers provide you with performance-optimized, consistentenvironments that can help you prototype and implement workflows quickly.

To learn more, see theDeep Learning Containersdocumentation.

Using Deep Learning Containers

You can use a Deep Learning Containers instance as a partof your work in Vertex AI. For example, theprebuilt containersavailable on Vertex AIare integrated Deep Learning Containers.

You can also build your Vertex AI model as acustom container-based applicationto help you deploy it in a consistent environment and run it whereverit needs to be.

To get started building your own custom container, follow these steps:

1. Choose one of the availablecontainerimages.

2. See the relevant Vertex AI documentation on containerrequirements, such asCustom containers fortrainingandCustom container requirements forprediction.

   Consider these requirements and prepare to modify yourcontainer accordingly.

3. Create a Deep Learning Containers localinstance,while making sure to modify the container according toVertex AI requirements.

4. Push the container toArtifact Registry.

What's next

• ReadIntroduction toDeep Learning VMto learn more about the product's features and capabilities.

• To get started using Deep Learning VM, create a newinstanceusingCloud Marketplaceorusing the commandline.

• ReadDeep Learning Containersoverviewto learn more about the product's features and capabilities.

• To get started using Deep Learning Containers,createa local deep learningcontainer.