nswamy commented on a change in pull request #13411: [WIP] Gluon end to end tutorial URL: https://github.com/apache/incubator-mxnet/pull/13411#discussion_r237704470
########## File path: docs/tutorials/gluon/gluon_from_experiment_to_deploymen.md ########## @@ -0,0 +1,400 @@ +# Gluon: from experiment to deployment, an end to end example + +## Overview + +MXNet Gluon API comes with a lot of great features and it can provide you everything you need from experiment to deploy the model. +In this tutorial, we will walk you through a common used case on how to build a model using gluon, train it on your data, and deploy it for inference. + +Let's say you want to build a service that provides flower species recognition. A common use case is, you don't have enough data to train a good model like ResNet50. Review comment: Let's say you want to build a service that recognizes different species of flowers and you do not have enough data to train model. In such cases we use a technique called Transfer Learning. In Transfer Learning we make use of a pre-trained model that solves a related task but is trained on a very large standard dataset such as ImageNet from a different domain, we utilize the knowledge in this pre-trained model to perform a new task at hand. Gluon provides State of the Art models for many of the standard tasks such as Classifcation, Object Detection, Segmentation, etc., In this example we will use the pre-trained model ResNetXX(link to paper) trained on ImageNet dataset, this model achieves XX accuracy on ImageNet, we seek to transfer as much knowledge as possible for our task of recognizing different species of Flowers. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
