Google Vertex AI Vision

  • Author: Ronald Fung

  • Creation Date: 14 June 2023

  • Next Modified Date: 14 June 2024

A. Introduction

Vertex AI Vision is an AI-powered platform to ingest, analyze and store video data. Vertex AI Vision lets users build and deploy applications with a simplified user interface.

Using Vertex AI Vision you can build end-to-end computer image solutions by leveraging Vertex AI Vision’s integration with other major components, namely Live Video Analytics, data streams, and Vision Warehouse. The Vertex AI Vision API allows you to build a high level app from low level APIs, and create and update a high level workflow that combines multiple individual API calls. You can then execute your workflow as a unit by making a single deploy request to the Vertex AI Vision platform server.

Using Vertex AI Vision, you can:

  • Ingest real-time video data

  • Analyze data for insights using general and custom vision AI models

  • Store insights in Vision Warehouse for simplified querying and metadata information

B. How is it used at Seagen

Google Vertex AI Vision is a suite of machine learning tools and services that enable businesses to build and deploy computer vision models on Google Cloud. Here are some ways that Seagen can use Google Vertex AI Vision to improve their computer vision processes:

  1. Data Preparation: Google Vertex AI Vision provides tools for data preparation and cleaning, enabling businesses to prepare their data for computer vision tasks. Seagen can use Google Vertex AI Vision to clean and preprocess their data, ensuring that it is ready for computer vision tasks.

  2. Model Training: Google Vertex AI Vision provides tools for model training, enabling businesses to train computer vision models quickly and efficiently. Seagen can use Google Vertex AI Vision to train their computer vision models and ensure that they are accurate and effective.

  3. Model Selection: Google Vertex AI Vision provides tools for model selection, enabling businesses to select the best computer vision model for their specific use case. Seagen can use Google Vertex AI Vision to evaluate and compare different computer vision models and select the best one for their needs.

  4. Model Deployment: Google Vertex AI Vision provides tools for model deployment, enabling businesses to deploy their computer vision models in production environments quickly and easily. Seagen can use Google Vertex AI Vision to deploy their computer vision models and ensure that they are performing as expected.

  5. AutoML: Google Vertex AI Vision provides AutoML tools that enable businesses to automatically build, train, and deploy computer vision models without requiring extensive machine learning expertise. Seagen can use Google Vertex AI Vision AutoML to build and deploy computer vision models quickly and efficiently, without the need for extensive machine learning expertise.

By using Google Vertex AI Vision, Seagen can improve their computer vision processes, accelerate time-to-market for their products, and reduce the risk of errors and downtime. Google Vertex AI Vision provides a range of tools and services that enable businesses to build and deploy computer vision models on Google Cloud, making it a powerful solution for computer vision tasks.

C. Features

Google Vertex AI Vision is a suite of machine learning tools and services that enable businesses to build and deploy computer vision models on Google Cloud. Here are some key features of Google Vertex AI Vision:

  1. AutoML Vision: Google Vertex AI Vision provides AutoML tools that enable businesses to automatically build, train, and deploy computer vision models without requiring extensive machine learning expertise. AutoML Vision enables businesses to build custom computer vision models that are tailored to their specific use cases.

  2. Pre-Trained Models: Google Vertex AI Vision provides pre-trained computer vision models that businesses can use to perform common computer vision tasks, such as image classification, object detection, and face recognition. These pre-trained models can be customized to meet the specific needs of the business.

  3. Custom Training: Google Vertex AI Vision provides tools for custom training of computer vision models, enabling businesses to train models using their own data sets. This enables businesses to build computer vision models that are specific to their use cases and data sets.

  4. High Accuracy: Google Vertex AI Vision provides state-of-the-art computer vision technology that enables businesses to achieve high accuracy in their computer vision models. This enables businesses to perform complex computer vision tasks with high levels of accuracy and reliability.

  5. Model Export: Google Vertex AI Vision enables businesses to export their computer vision models to other platforms, such as TensorFlow, so that they can be used in other applications and environments.

  6. Deployment: Google Vertex AI Vision provides tools for model deployment, enabling businesses to deploy their computer vision models in production environments quickly and easily. This enables businesses to integrate their computer vision models into their existing applications and workflows.

By providing these features, Google Vertex AI Vision enables businesses to build and deploy custom computer vision models that are tailored to their specific needs and use cases. This enables businesses to perform complex computer vision tasks with high levels of accuracy and reliability, ultimately improving their operational efficiency and reducing the risk of errors and downtime.

D. Where Implemented

LeanIX

E. How it is tested

Testing Google Vertex AI Vision involves verifying that the computer vision models are accurate, effective, and performing as expected. Here are some steps you can take to test Google Vertex AI Vision:

  1. Define Computer Vision Tasks: Define the computer vision tasks for your application, such as image classification or object detection. Create the necessary data sets and configurations needed for the computer vision model to be built and trained.

  2. Build Computer Vision Models: Build the computer vision models using the necessary tools and verify that the build process is successful. This can include checking that all data sets are included, that the model is built correctly, and that any tests have passed.

  3. Train Computer Vision Models: Train the computer vision models using the necessary tools and verify that the training process is successful. This can include checking that the model is accurate and effective and that any training metrics meet the desired thresholds.

  4. Deploy Computer Vision Models: Deploy the computer vision models to your target environment, such as a Google Cloud project, and verify that it works correctly. This can include testing that the model is accessible, that it performs as expected, and that there are no errors or bugs.

  5. Monitor Performance: Monitor the performance of the computer vision models to ensure that they are stable, accurate, and performing as expected. This can include monitoring model accuracy, performance metrics, and other model-specific metrics.

  6. Perform A/B Testing: Perform A/B testing to compare the performance of different computer vision models and ensure that they meet the desired performance thresholds.

By following these steps, you can test Google Vertex AI Vision and ensure that your computer vision model building, training, and deployment process is working correctly and producing the expected results. It’s important to regularly test your computer vision models to ensure that they remain accurate, effective, and reliable and to avoid costly errors or downtime.

F. 2023 Roadmap

????

G. 2024 Roadmap

????

H. Known Issues

While Google Vertex AI Vision is a powerful suite of machine learning tools and services for computer vision, there are some known issues or limitations that you should be aware of. Here are some of the common issues with Google Vertex AI Vision:

  1. Limited Customization: While Google Vertex AI Vision provides tools for computer vision model building, training, and deployment, the customization options may be limited for more complex computer vision models. It’s important to review the customization options and ensure that they meet the specific needs of your application.

  2. Cost: Google Vertex AI Vision is a paid service, and the cost can increase significantly for businesses with large or complex computer vision models. It’s important to review the pricing structure and estimate the cost of the service for your specific needs.

  3. Limited Integration with Non-Google Services: While Google Vertex AI Vision integrates well with other Google services, it may not integrate with all third-party services or tools. It’s important to review the integration options and ensure that all necessary integrations are supported.

  4. Limited Support for Certain Computer Vision Tasks: While Google Vertex AI Vision supports a wide range of computer vision tasks, it may not support all tasks or algorithms. It’s important to review the supported tasks and ensure that they meet the specific needs of your application.

  5. Limited Training Data Availability: Google Vertex AI Vision relies on training data to build accurate computer vision models. If there is limited training data available for a specific use case, it may be difficult to build an accurate model. It’s important to review the availability of training data and ensure that there is enough data to build an accurate model.

It’s important to be aware of these limitations and issues when using Google Vertex AI Vision. By understanding these challenges, you can better ensure that your computer vision processes remain reliable and efficient and avoid costly errors or downtime.

[x] Reviewed by Enterprise Architecture

[x] Reviewed by Application Development

[x] Reviewed by Data Architecture