Principal Data Scientist
Alexey lives in Berlin with his wife and son. He works as a lead data scientist at OLX and he runs DataTalks.Club — a community for data enthusiasts.
Alexey wrote a few books about machine learning. One of them is Machine Learning Bookcamp — a book for software engineers who want to get into machine learning.
How can we use AWS lambda and Tensorflow to serve deep learning models
Deep learning achieves the best performance for many computer vision, natural language processing, and recommendation tasks and thus it’s becoming increasingly more popular.
However, it’s quite difficult to use deep learning in production as it requires a lot of effort to develop proper infrastructure for serving deep learning models.
Platforms for serverless computing, such as AWS Lambda, provide a good alternative: they take care of scaling up and down and offer attractive pricing based only on actual usage. These platforms, unfortunately, have other limitations that make it problematic.
In this talk, we show how to come around these limitations and be able to use AWS lambda and TensorFlow to serve deep learning models. We’ll also cover the limitations of AWS lambda, compare it with “serverful” solutions, and suggest workloads for which serverless is not the best option.