Serverless deep learning; or, How to port your TensorFlow model to AWS Lambda
This year TensorFlow 1.4 was released. Rustem Feyzkhanov explains how he ported it to AWS Lambda and built an image recognition tool. The tool is cheaper than almost any alternatives and very scalable (a thousand functions can be run in parallel), and it integrates into cloud infrastructure.
Talk Title | Serverless deep learning; or, How to port your TensorFlow model to AWS Lambda |
Speakers | Rustem Feyzkhanov (Instrumental) |
Conference | O’Reilly Open Source Convention |
Conf Tag | Put open source to work |
Location | Portland, Oregon |
Date | July 16-19, 2018 |
URL | Talk Page |
Slides | Talk Slides |
Video | |
This year TensorFlow 1.4 was released. Rustem Feyzkhanov explains how he ported it to AWS Lambda and built an image recognition tool. The tool is cheaper than almost any alternatives: one run (recognition of one picture) will cost $0.00005. It’s also very scalable (a thousand functions can be run in parallel) and integrates into cloud infrastructure. Topics include: