IBM PowerAI Vision 1.1.5
IBM PowerAI Vision is a new generation video/image analysis platform that offers built-in deep learning models that learn to analyze images and video streams for classification and object detection.
PowerAI Vision includes tools and interfaces that allow anyone with limited skills in deep learning technologies to get up and running quickly and easily. And because PowerAI Vision 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 Developer learning path
Getting started with PowerAI Vision
This learning path is designed for developers interested in quickly getting up to speed on what PowerAI Vision offers and how to use it. The learning path consists of step-by-step tutorials, deep-dive videos, and complete examples of working code.
Technology updates and features
PowerAI 1.1.5 builds upon previous releases and includes the following updates and features:
- Support for DICOM images
The DICOM format is a widely used standard for processing medical images.
- Red Hat OpenShift support
You can now install PowerAI Vision on an OpenShift cluster.
- Integration with MaximoÂ® Asset Monitor
Maximo Asset Monitor is a cloud service that enables users to remotely monitor devices at the edge. This integration allows PowerAI Vision to send inference results to the Maximo Asset Monitor cloud platform for further analysis. See Integrating PowerAI Vision with Maximo Asset Monitor for more information.
- SSD model support
SSD models are suitable for real-time inference but are not as accurate as Faster R-CNN. For more information, see Training a model for more information.
- GoogLeNet and tiny YOLO V2 model Core ML support
See Training a model for more information.
- TensorRT support
Single Shot Detector and Faster R-CNN models are now enabled for TensorRT. See Training a model for more information.
- Python 3 support for custom models
Custom models must conform to Python 3. Any trained custom models from releases prior to Version 1.1.5 will not work if the custom model only supports Python 2. For more information about custom models, see Preparing a model that will be used to train data sets in PowerAI Vision.
- PyTorch custom model support
Imported custom models can now be PyTorch or TensorFlow based.
- Multiple improvements to the user interface
For all the details, see the Whatâ€™s New topic in the IBM Knowledge Center.
- Streamlined model training
Ue 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.
- IBM Power System AC922 with NVIDIA Tesla V100 GPUs
Supported operating systems
- Red Hat Enterprise Linux 7.6 for ppc64le
- Ubuntu 18.04 or later
- Planning information
- Install information
- Usage examples
Give it a try
PowerAI Vision code patterns, tutorials, and learning paths
Check out these real world examples and tutorials that highlight PowerAI Vision 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 PowerAI Vision
- PowerAI Vision GTC Presentation
- Build a classifier walkthrough with PowerAI Vision (video)
- See how to train models to analyze videos for Advanced Driver Assistant System (video)
- Download a sample dataset for classifying breeds of dogs from Stanford University
- IBM Power Systems AC922 (Models 8335-GTC, 8335-GTW)
- Ask a Support Question
- Email us for partnering and running Proof of Concepts
Requesting enhancements for IBM PowerAI Vision
The IBM Request for Enhancement (RFE) tool is now available for you to submit formal enhancement requests to the PowerAI Vision 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 PowerAI Vision 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 â€śSearchâ€ť 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.