This is the code repository for Advanced Computer Vision with TensorFlow [Video], published by Packt. It contains all the supporting project files necessary to work through the video course from start to finish.
TensorFlow has been gaining immense popularity over the past few months, due to its power and simplicity to use. This video will help you leverage the power of TensorFlow to perform advanced image processing. This course is a continuation of the Intro to Computer Vision course, building on top of the skills learned in that course. In this course, you’ll dive deeper as we cover more advanced computer vision concepts.
You will implement multiple state-of-the-art deep learning papers from scratch using the TensorFlow-Keras API. This course will teach you how to construct efficient CNN architectures with CNN Squeeze layers and delayed downsampling . You’ll learn about residual learning with skip connections and deep residual blocks, and see how to implement a deep residual neural network for image recognition. You’ll find out about Google’s Inception module and depthwise separable convolutions and understand how to construct an extreme Inception architecture with TF-Keras.
Finally, you’ll be introduced to the exciting new world of adversarial neural networks, which are responsible for recent breakthroughs in synthetic image generation and implement an auxiliary conditional GAN.
- Those who are new to TensorFlow will get an introduction to TensorFlow 1.X so that you appreciate the new features in 2.0
- In TensorFlow, you need a special way of writing the code using the Graph Mode and Eager Execution.
- Learn complicated concepts such as computation graphs, sessions, placeholders and more.
- All the new features that are now introduced in TensorFlow 2.0
- With the demo code, you will quickly learn how to apply these new features.
- You'll understand how to use Eager Execution in an effective manner
- You will learn about the upgrade tool which helps in upgrading your existing TF1.0 code to make it compatible with TF2.0
- Learn how image recognition works and how it is implemented using Convolutional Neural Networks and what’s new in TF2.0
- How to apply transfer learning and train your network faster with fewer data.
- Learn about Recurrent neural networks (RNN) and how they are improved in TF2.0
To fully benefit from the coverage included in this course, you will need:
This course is for Python developers who are interested in learning how to perform image processing using TensorFlow. A basic knowledge of TensorFlow will help you understand the concepts better.
This course has the following software requirements:
- Intel i3 processor
- 4 GB RAM
- 1TB hard disk
- Nvidia 210 GPU