Learning Computer Vision with TensorFlow

TensorFlow has gained immense popularity over the past few months, owing to its power and ease of use. This video aims to help you leverage the power of TensorFlow to do image processing. Beginning with an introduction to image processing, the video will take you through TensorFlow's API-like graph tensor, which is generally used for image classification. Starting off with basic 2D images, the video will gradually take you through recognizing more complex images, colors, shapes, and so on. Making use of the Python API, you will move on to classifying and training your model to identify objects in an image. Then you will learn about Convolutional Neural Networks, its architecture and why they perform well in the image takes. You will dive into the different layers available in TensorFlow. Further, we will construct the neural network feature extractor to embed images into a dense and rich vector space and finally perform fine-tuning optimization using pre-trained neural networks. Style and Approach. This video is a practical guide to implementing TensorFlow in production. It explores various scenarios in which you can use TensorFlow and shows you how to use it in the context of real-world projects. This will not only give you the upper hand in the field but shows the potential for innovative uses of TensorFlow in your environment. 

Target Audience  

Python developers who are interested in learning how to perform image processing using TensorFlow will benefit from this course. A basic knowledge of TensorFlow will help you understand concepts more effectively. 

Business Outcomes 

• Learn how to build a fully-fledged image-processing application using free tools and libraries
• Perform basic to advanced image (as well as video) stream processing with Python's APIs
• Understand and optimize various features of TensorFlow with the help of easy-to-grasp examples