|AWS DeepLens Available for Pre-Order|
|Written by Kay Ewbank|
|Friday, 25 May 2018|
A video camera for developers that is enabled for deep learning is available for pre-order on Amazon.
AWS DeepLens is a wireless video camera and API that can be used to learn how to use AI tools and technology to develop real-time computer vision apps. Deep learning is a machine learning technique that uses neural networks to learn and make predictions. The camera uses deep convolutional neural networks (CNNs) to analyze images. It works with a number of AWS services, including Amazon SageMaker, for model training and validation; AWS Lambda, for running inference against CNN models; and AWS Greengrass, for deploying updates and functions to your device.
SageMaker is Amazon's machine learning platform that can be ued to build, train, and deploy ML models in the cloud. Lambda is a serverless compute service that runs your code in response to events and automatically manages the underlying compute resources for you. It has support for Python functions so can be used to run machine learning algorithms.
Greengrass is software that extends AWS cloud capabilities to local devices so they can collect and analyze data locally. Developers who use AWS Greengrass can author serverless code (AWS Lambda functions) in the cloud and deploy it to devices for local execution of applications. Developers can run Node.js or Python functions within Greengrass. The most likely use of DeepLens will be to use the AWS services to carry out the deep learning on the images. SageMaker will be used to build and train a CNN in the AWS cloud, then deploy it to DeepLens.
AWS DeepLens lets you run deep learning models locally on the camera to analyze and take action on what it sees. The thought of running learning models locally might seem unachievable, but the camera includes a PC based on an Intel Atom X5 Processor with 8GB of RAM, 16GB storage, four cores and four threads. It also has an Intel Gen9 Graphics Engine embedded GPU.The camera sends video frames to an AWS Lambda function that runs the ML inference model written in Python. The camera comes with tools to help developers get started quickly, including six sample projects, pre-trained models, tutorials, and code. In addition to SageMaker, Greengrass and Lambda, the camera works with Amazon Rekognition for image and video analysis, and Amazon Polly for speech-enabled projects.Apache MXNet is the machine learning framework being used for DeepLens. MXNet is Apache's deep learning framework.
or email your comment to: email@example.com
|Last Updated ( Friday, 25 May 2018 )|