TensorFlow is popular a library for implementing a range of deep learning solutions but is especially useful for solutions that deal with images. This course will teach you the basics of how to use TensorFlow to implement the most typical scenarios.
Running images through deep learning models is potentially the most typical scenario in which deep learning is
used today. In this course, Implementing Image Recognition Systems with TensorFlow, you will learn the basics of how to implement a solution for the most typical deep learning imaging scenarios. First, you will learn how to pick a TensorFlow model architecture if you can implement your solution with pre-existing, pre-trained models. Next, you will learn how to extend such models using your own training images by taking advantage of transfer learning. Finally, you will see how to use more advanced solutions to do more advanced processing on images, like segmentation, and even learn how to implement a facial recognition solution. When you are finished with this course, you will have the skills and knowledge of TensorFlow and imaging in order to implement your own solutions successfully.
Although Jon spent the first few years of his professional life as an attorney, he quickly
found chasing bits more interesting than chasing ambulances. Since 2011, Jon has been concentrating on the mobile world. Working mainly in iOS, Jon
has helped numerous companies create and transform mobile teams into teams that can
create, build, test, and deploy mobile applications with ease.
Course Overview Hey everyone. My name is Jon Flanders, and welcome to my course, Implementing Image Recognition Systems with TensorFlow. I'm a software architect and developer with over 20 years of experience in the industry, the last few spending most of my time working with technologies, such as machine learning and augmented reality. Running images through deep learning models is potentially the most typical scenario in which deep learning is used today. In this course you will learn the basics of how to implement a solution for the most typical deep learning imaging scenarios. Specifically we'll cover, number one, how to pick a TensorFlow model; two, how to use transfer learning; three, how to get more than just classification from a model; and four, how to implement facial recognition. By the end of this course you'll know the basics of working with TensorFlow and imaging in order to be able to successfully implement your own solutions. I hope you'll join me on this journey to learn TensorFlow and imaging with the Implementing Image Recognition Systems with TensorFlow course at Pluralsight.