Building an Image Classifier in TensorFlow Using Python - A Step-by-Step Approach
Kumar Nityan Suman (~nityansuman) |
Description:
Image classification refers to the task of extracting information classes from a images by learning features of the images. Image classification is perhaps the most important part of digital image analysis.
TensorFlow
is an open-source machine learning library for research and production. TensorFlow
offers APIs for beginners and experts to develop for desktop, mobile, web, and cloud. TensorFlow
is a great and popular machine learning library which can be used to implement almost any machine learning algorithms in a convenient and efficient manner.
In this workshop I will be showing you how to create a multi-layer neural network using tensorflow from scratch and in a very simple manner. We'll be creating multiple neural network to classify images of of clothing
, like sneakers, pants, bags and shirts and see the advantages of one over the other. We'll also go through the theory and mathematics behind the algorithm is use so that you can build your own with a different dataset whenever needed.
Outline/Structure of the workshop:
- Understanding the problem statement
- Investigating and pre-processing data as necessary
- Understanding theory behind the magic
- Writing a model
- Training and Evaluating the model
- Retrospect
Learning Outcome:
- Investigating data from a Data Scientist's perspective.
- Creating models in TensorFlow.
- Understanding workflow of a deep learning project.
- Understanding how image classifiers work.
Prerequisites:
- Familiarity with
Python
- Basic understanding of
How neural networks work.
(Optional)
Content URLs:
- https://github.com/nityansuman/fashion-attire-classification
- https://www.tensorflow.org/tutorials/keras/basic_classification (Core Link)
- http://desktop.arcgis.com/en/arcmap/latest/extensions/spatial-analyst/image-classification/what-is-image-classification-.htm
Speaker Info:
Nityan is a seasoned Data Scientist
at Youplus Inc. with sound experience in solving real world business problems across domains of Natural Language Processing and Computer Vision.
He has been working in the domain of natural language processing for quite some time now and has experience of more than a dozen NLP
and Computer Vision
projects ranging from Image Classification, Text Classification, Text Similarity, Anaphora Resolution to advanced topics such as Aspect Based Sentiment Classification, Question-Answering, Video Classification.
He is a data science evangelist. He mentors university level teams for state and national level hackathons. He himself have won the prestigious MLADS hackathon organized by Microsoft India. He also maintains a couple of Open-Source projects on the side for fun.
Speaker Links:
LinkedIn: https://linkedin.com/in/kumar-nityan-suman/
GitHub: https://github.com/nityansuman/
Twitter: https://twitter.com/im_nityan/