Chris Fregly - High-Performance Distributed Tensorflow
Title High-Performance Distributed Tensorflow: Request Batching and Model Post-Processing Optimizations
Filmed at PyData London 2017
Description
In this completely demo-based talk, Chris will demonstrate various techniques to post-process and optimize trained Tensorflow AI models to reduce deployment size and increase prediction performance.
Abstract
In this completely demo-based talk, Chris will demonstrate various techniques to post-process and optimize trained Tensorflow AI models to reduce deployment size and increase prediction performance.
First, we'll use various techniques such as 8-bit quantization, weight-rounding, and batch-normalization folding, we will simplify the path of forward propagation and prediction.
Next, we'll loadtest and compare our optimized and unoptimized models - in addition to enabling and disabling request batching.
Last, we'll dive deep into Google's Tensorflow Graph Transform Tool to build custom model optimization functions.
www.pydata.org
PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R.
We aim to be an accessible, community-driven conference, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!
00:10 Help us add time stamps or captions to this video! See the description for details.
Want to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVi...
Смотрите видео Chris Fregly - High-Performance Distributed Tensorflow онлайн, длительностью часов минут секунд в хорошем качестве, которое загружено на канал PyData 06 Май 2017. Делитесь ссылкой на видео в социальных сетях, чтобы ваши подписчики и друзья так же посмотрели это видео. Данный видеоклип посмотрели 1,722 раз и оно понравилось 13 посетителям.
