AWS Machine Learning Blog

Category: Apache MXNet on AWS*

Apache MXNet Model Server adds optimized container images for Model Serving at scale

Today AWS released Apache MXNet Model Server (MMS) v0.3, which streamlines the deployment of model serving for production use cases. The release includes pre-built container images that are optimized for deep learning workloads on GPU and CPU. This enables engineers to set up a scalable serving infrastructure. To learn more about Apache MXNet Model Server […]

Read More

Text Classification with Gluon on Amazon SageMaker and AWS Batch

Our customer had a problem: The manual classification of warranty claims was causing a bottleneck. These claims were based on a text field that explained the event in short detail. An example of that text looked something like this: “The plutonium-fueled nuclear reactor overheated on a hot day in Arizona’s recent inclement weather. Burn damage […]

Read More

Model Server for Apache MXNet introduces ONNX support and Amazon CloudWatch integration

Today AWS released version 0.2 of Model Server for Apache MXNet (MMS), an open-source library that packages and serves deep learning models for making predictions at scale. Now you can serve models in Open Neural Network Exchange (ONNX) format and publish operational metrics directly to Amazon CloudWatch, where you can create dashboards and alarms. What […]

Read More

Speeding up Apache MXNet using the NNPACK library

Apache MXNet is an open source library developers can use to build, train, and re-use deep learning networks. In this  blog post, I’ll show you to speed up inference by using the NNPACK library. Indeed, when GPU inference is not available, adding NNPACK to Apache MXNet might be a simple option to extract more performance […]

Read More

Updated AWS Deep Learning AMIs: New Versions of TensorFlow, Apache MXNet, Keras, and PyTorch

We’re excited to update the AWS Deep Learning AMIs with significantly faster training on NVIDIA Tesla V100 “Volta” GPUs across many frameworks, including TensorFlow, PyTorch, Keras, and the latest Apache MXNet 1.0 release. There are two main flavors of the AMIs available today. The Conda-based AWS Deep Learning AMI packages the latest point releases of […]

Read More

Introducing Model Server for Apache MXNet

Earlier this week, AWS announced the availability of Model Server for Apache MXNet, an open source component built on top of Apache MXNet for serving deep learning models. Apache MXNet is a fast and scalable training and inference framework with an easy-to-use, concise API for machine learning. With Model Server for Apache MXNet, engineers are […]

Read More

Announcing the Availability of ONNX 1.0

Today, Amazon Web Services (AWS), Facebook and Microsoft are pleased to announce that the Open Neural Network Exchange (ONNX) format is production ready. ONNX is an open standard format for deep learning models that enables interoperability between deep learning frameworks such as Apache MXNet, Caffe2, Microsoft Cognitive Toolkit, and PyTorch. ONNX 1.0 enables users to […]

Read More

AWS Contributes to Milestone 1.0 Release of Apache MXNet Including the Addition of a New Model Serving Capability

Today AWS announced contributions to the milestone 1.0 release of the Apache MXNet deep learning engine and the introduction of a new model serving capability for MXNet. These new capabilities (1) simplify training and deploying deep learning models, (2) enable implementation of cutting-edge performance enhancements, and (3) provide easy interoperability between deep learning frameworks. In […]

Read More

Distributed Inference Using Apache MXNet and Apache Spark on Amazon EMR

In this blog post we demonstrate how to run distributed offline inference on large datasets using Apache MXNet (incubating) and Apache Spark on Amazon EMR. We explain how offline inference is useful, why it is challenging, and how you can leverage MXNet and Spark on Amazon EMR to overcome these challenges. Distributed inference on large […]

Read More

Run Deep Learning Frameworks with GPU Instance Types on Amazon EMR

Today, AWS is excited to announce support for Apache MXNet and new generation GPU instance types on Amazon EMR, which enables you to run distributed deep neural networks alongside your machine learning workflows and big data processing. Additionally, you can install and run custom deep learning libraries on your EMR clusters with GPU hardware. Through […]

Read More