IBM Visual Insights 1.2.0
IBM Visual Insights 1.2.0, formerly PowerAI Vision, is a video/image analysis platform that offers built-in deep learning models that learn to analyze images and video streams for classification and object detection.
IBM Visual Insights includes tools and interfaces that allow anyone with limited skills in deep learning technologies to get up and running quickly and easily. And because IBM Visual Insights is built on open source frameworks for modeling and managing containers it delivers a highly available platform that includes application life-cycle support, centralized management and monitoring, and support from IBM.
IBM PowerAI Vision is now IBM Visual Insights
To accommodate the diversity of infrastructures used for AI solutions, IBM has expanded support of its award-winning software beyond POWER architectures to include Intel platforms. To avoid confusion in the marketplace, IBM PowerAI Vision has been renamed IBM Visual Insights. In addition to its current functions, IBM Visual Insights 1.2.0 now offers:
- Support on x86-based servers with GPUs for training and inference
- Availability on IBM Cloud as a client-managed service
- The installation location has changed from
/opt/powerai-visionto an IBM standard location:
- Runtime tools have removed
powerai-from the tool names. For example,
- Runtime Docker container and Kubernetes pod names have removed
powerai-from the name
Technology updates and features
IBM Visual Insights 1.2.0 builds upon previous releases of PowerAI Vision, and includes the following updates and features:
Platform support expanded:
- Training and Inference on x86 servers with Nvidia GPU acceleration. Full feature parity – model support and function.
- Inference Server support parity on x86. Support for SSD object detection model deployment.
- IBM Cloud beta deployment.
- Enhanced post-processing support: Automatic population of data set with inference results.
- Update of User Interface: IBM Carbon X – improved support for tablet format.
- Improved handling of phone images: EXIF processing/rotation on image load.
For all the details, see the What’s New topic in the IBM Knowledge Center.
- Streamlined model training
Use existing models that are already trained as starting point to reduce the time required to train models and improve trained results.
- Single-click model deployment
After you create a training model, deploy an API with one click. You can then develop applications based on the model that you deployed.
- Data set management and labeling
Manage both raw and labeled data.
- Video object detection and labeling assistance
Videos that you import can be scanned for objects and the objects can be automatically labeled.
- POWER8 S822LC (8335-GTB) or POWER9 AC922 with at least one NVIDIA NVLink capable GPU
- POWER9 IC922 with at least one NVIDIA T4 GPU
- x86 system with at least one NVIDIA Pascal, Volta, or Turing-architecture GPU
- 64 GB of memory
Supported operating systems
- Red Hat Enterprise Linux (RHEL) RHEL 7.6 ALT (little endian) for POWER9™
- Ubuntu 18.04 or later
- RHEL 7.7 for x86
- Planning information and considerations
- Install information
- Training and working with models
Give it a try
IBM Visual Insights (and PowerAI Vision) code patterns, tutorials, and learning paths
Check out these real world examples and tutorials that highlight IBM Visual Insights in action.
Additional resources to help you get started
- Image Classification & Object Detection on IBM PowerAI Vision
- ProMare: Unlocking the secrets of the ocean with an autonomous ship operated by AI and edge technology
- Oxford Cancer Biomarkers (OCB): Combining leading-edge diagnostics with AI technology to improve outcomes for cancer patients
- AI solutions in Energies and Utilities with IBM PowerAI Vision
- Computer Vision made simple with IBM PowerAI Vision
- IBM Marketplace for IBM Visual Insights
- Ask a Support Question
- Email us for partnering and running Proof of Concepts
Requesting enhancements for IBM Visual Insights
The IBM Request for Enhancement (RFE) tool is now available for you to submit formal enhancement requests to the IBM Visual Insights development team. One of the benefits of using the RFE tool is that other clients can vote on submitted requirements, which helps IBM to prioritize requests.
Go here get started: ibm.biz/vision-rfe
The RFE for IBM Visual Insights pages are part of IBM Developer and require that you sign in with an IBM ID to submit or vote on a request. You should make sure that your IBM ID profile includes your current company and your email address to ensure that we can contact you if we have questions.
Once on the RFE page, click on the “Search” tab to view existing requests before you submit a new request. It is much more useful to vote for a previously submitted request than to submit a duplicate request.
We recommend that you install the most current release of IBM Visual Insights, however, if you have an earlier version of PowerAI Vision installed, you can find release information in the IBM Knowledge Center: