Leveraging oneAPI Containers to Deploy OpenVINO™ Notebooks for Efficient AI Research
This presentation will demonstrate how to use Apptainer containers to deploy Intel OpenVINO Jupyter notebooks for an optimized AI research workflow. OpenVINO is Intel’s toolkit for deploying pre-trained deep learning models and optimizing model inference. The oneAPI containers package all the required software dependencies in a self-contained unit. Apptainer enables seamless integration of these containers into HPC clusters such as Digital Research Alliance of Canada, which provides Canadian researchers with the support they need for leading-edge research excellence, research, innovation and advancement across all disciplines.
We will demo the performance benefits of running OpenVINO notebooks in Apptainer for rapidly prototyping and iterating on neural network architectures. The containers grant access to accelerated model training and inference on Intel CPUs and GPUs. We will also discuss how the Apptainer execution model provides security, reproducibility and portability for AI research.
Speaker(s)
Peter Darveau - Hexagon Technology Inc./Consultant to Research
Peter Darveau P. Eng., has more than 25 years of experience in AI, automation and robotics, and has worked with General Electric, General Motors, and NASA. He is a licensed consulting engineer, Intel AI Provider, oneAPI for ML instructor, and Six Sigma practitioner. He has published papers relating to automation, High-Performance Computing (HPC) and AI models, and has been cited internationally for work on machine learning models. Peter has spoken at events for GE and at a national level for Ontario Society of Professional Engineers (OSPE), Digital Research Alliance of Canada, and Society of Manufacturing Engineers (SME). He is actively involved with HPC in research and AI startups, and volunteers his time to coach and teach in his local engineering and francophone communities.
