Using Convolutional Neural Networks and TensorFlow for Image Classification

by Sophia TurolJune 30, 2016
Learn how convolutional neural networks enhance image classification and visual search by making edge detection, pixel segmentation, etc. more efficient.

tensorflow-new-york-meetup

At the recent NYC TensorFlow meetup, it was discussed how to train an image classifier with TensorFlow. From this blog post, you will learn about the challenges of image classification / search and how to address them with convolutional neural networks.

 

Training an image classifier with TensorFlow

In his session, Scott Thompson of KONTOR talked about:

When setting up image features (edge detection, color histogram, pixel segmentation, etc.) for classification or search, the job is mostly manual and takes time. According to Scott, convolutional neural networks provide a black box to construct image features. He also outlined some advantages of using a pretrained model:

  • It’s faster (as it’s pretrained already).
  • It’s cheaper (no need for GPU farm).
  • It generalizes (avoids overfitting).

Join the meetup group to stay informed about the upcoming events.

 

Want details? Watch the video!

 

 

Related slides

 

Further reading

 

About the speaker

Scott Thompson is a full-stack engineer who enjoys focusing on large-scale data mining, predictions, and recommendations. He is particularly interested in Scala, Clojure, and ClojureScript applications.