Alexander Bovyrin (Algorithm Innovation Lead, Sr. PE, Intel) Yury Gorbachev (Computer Vision SDK Lead Architect, PE, Intel) Vadim Pisarevsky (OpenCV Development Lead, PE, Intel)
Time: 13:30-17:30 (Half Day — Afternoon)
Deep Learning based algorithms are very resource demanding and compute intensive tasks. Selection of deployment tools is important choice that has to be made whenever algorithm is ready for production. In practice, selection of tools not only impacts speed, but also quality of the final solution. Hence, knowledge about target platform and features that are supported by enabling tools at algorithm selection stage can be critical.
This tutorial will provide introduction to Intel tools for deep learning deployment (Deep Learning Inference Engine and OpenCV DNN module) and will cover following important topics:
- Architecture of Deep Learning deployment tools;
- Cross-platform portability for DL deployment;
- Most important features (Topology specific optimizations, dynamic batching, support for various levels of precision, Inference Engine integration into OpenCV);
- Overview of CV SDK models zoo;
- Planned features.
Tutorial will also walk participants through actual examples of algorithm design (topology selection and quality evaluation) and workflow of porting to Intel DL Deployment tools. Performance figures for final solution as well as comparison with other Deep Learning solutions will be provided.
A G E N D A
|13:30 – 14:15||Architecture of Intel Deep Learning deployment tools|
|14:15 – 14:45||Cross-platform portability for DL deployment|
|14:45 – 15:30||Most important features (Topology specific optimizations, dynamic batching, support for various levels of precision, Inference Engine integration into OpenCV)|
|15:30 – 16:00||Coffee break.|
|16:00 – 16:20||Examples of deployment tools usage|
|16:20 – 16:40||CV SDK Models Zoo|
|16:40 – 17:00||Planned CV SDK features|
|17:00 – 17:30||Overview of R&D in deep nets optimization|