“ONNX (Open Neural Network Exchange): current status and beyond”
Harry Kim, Intel
When: Thursday, May 2, 10:30 am US Eastern.
Zoom Detail Below
Background:
Harry Kim is a Senior Staff Product Manager working on deep learning compiler project (nGraph) at Intel AI. Prior to Intel AI, he developed machine learning algorithms at Google for Ads and Fiber. He received Statistics Ph.D from University of California, Berkeley with emphasis on spatial analysis and real time prediction.
This talk will provide an overview of current progress for ONNX and its exciting features under development. ONNX is an open standard format for deep learning models that enables interoperability between deep learning frameworks such as TensorFlow, Caffe2, PyTorch etc. The ONNX stack has further evolved to provide suite of tools to deploy deep learning models for production. Summary of these tools (ONNXIFI, ONNX Runtime, ONNX.js) will be provided along with information on features under development (quantization & training) and new open governance structure.
Zoom meeting Link: https://zoom.us/j/7371462221
Zoom Callin: (415) 762-9988 or (646) 568-7788 Meeting id 7371462221
Zoom International Numbers: https://zoom.us/zoomconference
Check the website in case the date or time changes: http://cognitive-science.info/
Please retweet
Join LinkedIn Group https://www.linkedin.com/