Get Cloud Ready!

Janakiram MSV

Subscribe to Janakiram MSV: eMailAlertsEmail Alerts
Get Janakiram MSV via: homepageHomepage mobileMobile rssRSS facebookFacebook twitterTwitter linkedinLinkedIn

Blog Feed Post

Train a Convolutional Neural Network with Nvidia DIGITS and Caffe

In the previous part of this series, I introduced Nvidia DIGITS as a user-friendly interface to build Deep Learning models. In this tutorial, I will walk you through the steps involved in building a Convolutional Neural Network that can classify images. We will use the popular cat versus dog dataset to train our model. By the end of this tutorial, you will learn everything it takes to train the model with DIGITS and using it for inferencing.

You need a Linux machine with a GPU to build the model. For inferencing, any OS that can run Docker is sufficient.

Preparing the Environment

Let’s start by downloading the dataset on the host machine on which you will run Nvidia DIGITS container. The dataset is similar to the one used in Kaggle Dogs versus Cats competition. It contains about 4,000 images of cats and dogs which is just enough for the tutorial. The images are already resized to 256×256 to skip preprocessing.

Since the dataset is too big for Github, I uploaded it to Google Drive. Downloadthe file and unzip it in a folder. You should see two directories, train and test. The first directory contains 2,500 images of each category while the test directory has about 1,500 images.

Let’s launch Nvidia DIGITS Docker container by mapping the folder that contains the train and test directories. The dataset would become available at /data directory within the container.

$ docker run --runtime=nvidia --name digits -d -p 5000:5000 -v $PWD:/data nvidia/digits

Read the entire article at The New Stack

Janakiram MSV is an analyst, advisor, and architect. Follow him on Twitter,  Facebook and LinkedIn.

Read the original blog entry...

More Stories By Janakiram MSV

Janakiram MSV heads the Cloud Infrastructure Services at Aditi Technologies. He was the founder and CTO of Get Cloud Ready Consulting, a niche Cloud Migration and Cloud Operations firm that recently got acquired by Aditi Technologies. In his current role, he leads a highly talented engineering team that focuses on migrating and managing applications deployed on Amazon Web Services and Microsoft Windows Azure Infrastructure Services.
Janakiram is an industry analyst with deep understanding of Cloud services. Through his speaking, writing and analysis, he helps businesses take advantage of the emerging technologies. He leverages his experience of engaging with the industry in developing informative and practical research, analysis and authoritative content to inform, influence and guide decision makers. He analyzes market trends, new products / features, announcements, industry happenings and the impact of executive transitions.
Janakiram is one of the first few Microsoft Certified Professionals on Windows Azure in India. Demystifying The Cloud, an eBook authored by Janakiram is downloaded more than 100,000 times within the first few months. He is the Chief Editor of a popular portal on Cloud called www.CloudStory.in that covers the latest trends in Cloud Computing. Janakiram is an analyst with the GigaOM Pro analyst network where he analyzes the Cloud Services landscape. He is a guest faculty at the International Institute of Information Technology, Hyderabad (IIIT-H) where he teaches Big Data and Cloud Computing to students enrolled for the Masters course. As a passionate speaker, he has chaired the Cloud Computing track at premier events in India.
He has been the keynote speaker at many premier conferences, and his seminars are attended by thousands of architects, developers and IT professionals. His sessions are rated among the best in every conference he participates.
Janakiram has worked at the world-class product companies including Microsoft Corporation, Amazon Web Services and Alcatel-Lucent. Joining as the first employee of Amazon Web Services in India, he was the AWS Technology Evangelist. Prior to that, Janakiram spent 10 years at Microsoft Corporation where he was involved in selling, marketing and evangelizing the Microsoft Application Platform and Tools.