Using Docker Containers in the Deep Learning Platform FfDL

In order to train the object detection model for my sample, TensorFlow Object Detection for Anki Overdrive Cars, I used a custom Docker container. I've extended the description of my repo to also document how Fabric for Deep Learning (FfDL) can be used to run this container.

Fabric for Deep Learning (FfDL) is an open-source extension for Kubernetes to run Deep Learning workloads. It can be run in the cloud or on-premises. It supports frameworks like TensorFlow, Caffe and PyTourch, it's supports GPUs and can be used to run distributed trainings. Watson Deep Learning as a Service uses FfDL internally.

from DZone.com Feed https://ift.tt/2y7cXz2