Published in AWS Tip·PinnedHow AWS Lambda SnapStart drastically reduces cold starts for Serverless Machine Learning InferenceChallenges with cold start for ML inference One of the main challenges with Serverless Machine Learning Inference was always a cold start. And in the case of ML inference there are multiple things contributing to it: runtime initialization loading libraries and dependencies loading the model itself (from S3 or package) initializing the model Some of these steps…AWS4 min readAWS4 min read
Nov 14, 2022ML No/Low Code services and Use Cases @ Re:Invent 2022Machine Learning is becoming essential for a lot of industries, but setting ML projects for success is challenging and requires business context, data science knowledge as well as familiarity with the production stack. …AWS4 min readAWS4 min read
Nov 8, 202212 MLOps breakout sessions I’m looking forward to at Re:Invent 2022MLOps is a field of best practices for companies to run ML workflows in production. It encompasses a large stack of tasks from optimizing the pipeline for training and inference to the observability of the model in production. New tools and practices appear every year so here are the top…4 min read4 min read
Nov 26, 20217 things to know before using AWS PanoramaMachine learning is becoming essential for a lot of companies and they want to use it to optimize their operations and make new services. One of the challenges is that sometimes you need to deploy a model in an environment where you have limited internet connection and no operators to…AWS4 min readAWS4 min read
Nov 16, 20217 MLOps breakout sessions I’m looking forward to at Re:Invent 2021MLOps is an emerging field of best practices for businesses to run Machine Learning workflows in production. MLOps captures a very wide range of tasks from optimizing model inference in production to structuring training processes and data pipelines. New tools and practices appear every year so here are the top…Mlops3 min readMlops3 min read
Sep 29, 2021Machine Learning Inference on AWS Lambda Functions powered by AWS Graviton2 ProcessorsMachine Learning became a necessity for a lot of companies — from Fortune 500 companies to small startups. With all the frameworks and libraries available out there, it became a lot easier to start developing machine learning models. The new challenge is to architect a prediction pipeline in the cloud…Serverless5 min readServerless5 min read
May 6, 2021ML infrastructure @ AWS Summit 2021Organizing infrastructure for ML applications is a challenging task. Depending on your pipeline you may need to combine different types of virtual machines, organize research infrastructure as well as monitor the system. You may also need to have a way of maintaining ML infrastructure so it’s to deploy updates. …AWS2 min readAWS2 min read
Nov 30, 2020MLOps @ re:Invent 2020MLOps is an emerging field of best practices for businesses to run ML workflows in production. There are multiple challenges associated with MLOps which makes it different from traditional DevOps. From monitoring where you may need to monitor model performance and change in data to cost and scale optimizations where…Mlops2 min readMlops2 min read
Nov 18, 2020Training models using Satellite imagery on Amazon Rekognition Custom LabelsSatellite imagery is becoming a more and more important source of insights about changes that happen worldwide. There are multiple satellites that provide publicly available data with almost full earth coverage and almost weekly frequency. One of the main challenges with satellite imagery is to deal with getting insights from…Deep Learning5 min readDeep Learning5 min read