Dog breed image classification using transfer learning

Learn to build image classification engine with transfer learning

Ratings: 3.03 / 5.00




Description

Course Description

Learn to build image classification  engine with using Transfer Learning. Transfer learning is a techqniuqe where model learned from one task can be applied to another task with little bit of fine tuning.

Andrej Karpathy, AI director at Tesla has one said "Dont try to be hero just because you want to". What this means although you could develop image classification from scratch, doing it would take several days and requires huge computing resources and big dataset. A lot of smart researchers have already spent lot of time building really good image classification networks like VGGNET, RESNET, Inception V3. These networks have been trained on imagenet animal dataset. If your dataset requires a different type of image classification, you could just start with these networks and fine tune them on your smaller dataset. This saves significant time and resources.


Build a strong foundation in Transfer LEarning Search with this tutorial for beginners.

  • Understanding of transfer learning

  • Benefits of Transfer Learning

  • Learn how to apply transfer learning with real example

  • Understand basics of CNN and deep learning

  • Learn how CNN lends themselves useful for transfer learning

  • Leverage transfer learning to classify dog breed images

  • Use Jupyter Notebook for step by step programming

  • Build a real life web application for dog breed classification


  • A Powerful Skill at Your Fingertips  Learning the fundamentals of transfer learning  puts a powerful and very useful tool at your fingertips. Python and Jupyter are free, easy to learn, has excellent documentation.

No prior knowledge of transfer learning is assumed. I'll be covering topics like deep learning, CNN, transfer learning  from scratch.

Jobs in computer vision area are plentiful, and being able to learn transfer learning will give you a strong edge. Transfer learning is  state of art technology that can quickly help you achieve your goal.

Transfer learning is becoming very popular.  Learning image classification with transfer learning will help you become a computer vision developer which is in high demand.



Content and Overview  

This course teaches you on how to build dog breed classification engine using open source Python and Jupyter framework.  You will work along with me step by step to build following answers

  • Introduction to transfer learning

  • Introduction to CNN

  • Build an jupyter notebook step by step using BERT

  • Build a real world web application to find breed of dogs


What am I going to get from this course?

  • Learn transfer learning and build dog breed image classification engine from professional trainer from your own desk.

  • Over 10 lectures teaching you how to build image classification engine

  • Suitable for beginner programmers and ideal for users who learn faster when shown.

  • Visual training method, offering users increased retention and accelerated learning.

  • Breaks even the most complex applications down into simplistic steps.

  • Offers challenges to students to enable reinforcement of concepts. Also solutions are described to validate the challenges.

What You Will Learn!

  • Dog Breed Image classification using transfer learning
  • Understanding of transfer learning
  • Learn how CNN lends themselves useful for transfer learning
  • Build a real life web application for dog breed classification

Who Should Attend!

  • Begineer and intermediate python developers who are curious about computer vision