LEARNING PATH: TensorFlow: Computer Vision with TensorFlow
Learn image processing and neural networks with Tensorflow from scratch
Ratings 3.90 / 5.00
What You Will Learn!
- Learn to build powerful multiclass image classifiers
- Understand how to build a neural feature extractor that can embed images into a dense and rich vector space
- Perform fine-tuning optimization on new predictive tasks using pre-trained neural networks
- Build functional model class and methods with Keras
- Know how to choose the right loss function and evaluation metric for the right task
- Build a computational graph representation of a neural network
- Train a neural network with automatic back propagation
- Learn to optimize a neural network with stochastic gradient descent and other advanced optimization methods
Description
TensorFlow has been gaining immense popularity over the past few months, due to its power and simplicity to use. So, if you’re a Python developer who is interested in learning how to create applications and perform image processing using TensorFlow, then you should surely go for this Learning Path.
Packt’s Video Learning Path is a series of individual video products put together in a logical and stepwise manner such that each video builds on the skills learned in the video before it.
The highlights of this Learning Path are:
- Learn how to create image processing applications using free tools and libraries
- Perform advanced image processing with TensorFlowAPIs
- Understand and optimize various features of TensorFlow by building deep learning state-of-the-art models
Let's take a quick look at your learning journey. This Learning Path starts off with an introduction to image processing. You will then walk through graph tensor which is used for image classification. Starting with the basic 2D images, you will gradually be taken through more complex images, colors, shapes, and so on. You will also learn to make use of Python API to classify and train your model to identify objects in an image.
Next, you will learn about convolutional neural networks (CNNs), its architecture, and why they perform well in the image take. You will then dive into the different layers available in TensorFlow. You will also learn to construct the neural network feature extractor to embed images into a dense and rich vector space.
Moving ahead, you will learn to construct efficient CNN architectures with CNN Squeeze layers and delayed downsampling. You will learn about residual learning with skip connections and deep residual blocks, and see how to implement a deep residual neural network for image recognition. Next, you will find out about Google’s Inception module and depth-wise separable convolutions and understand how to construct an extreme Inception architecture with TF-Keras. Finally, you will 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 generative adversarial networks (GAN).
By the end of this Learning Path, you will be able to create applications and perform image processing efficiently.
Meet Your Expert:
We have the best work of the following esteemed author to ensure that your learning journey is smooth:
Marvin Bertin has authored online deep learning courses. He is the technical editor of a deep learning book and a conference speaker. He has a bachelor’s degree in mechanical engineering and master’s in data science. He has worked at a deep learning startup developing neural network architectures. He is currently working in the biotech industry building NLP machine learning solutions. At the forefront of next generation DNA sequencing, he builds intelligent applications with machine learning and deep learning for precision medicine.
Who Should Attend!
- This Learning Path is for Python developers who are interested in learning how develop applications and perform image processing using TensorFlow.
