English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 0h 55m | 210 MB
Visualize a variety of Neural Network architectures and even show how your pre-trained models process data in real-time
TensorSpace is a neural network 3D visualization framework built by TensorFlow.js, Three.js, and Tween.js. TensorSpace provides Keras-like APIs to build deep learning layers, load pre-trained models, and generate a 3D visualization in the browser.
By applying TensorSpace API, it is more intuitive for Data Scientists to visualize and understand any pre-trained models built by TensorFlow, Keras, TensorFlow.js, and so on.
In this quick and short course, you’ll learn how to present the inner workings of your pre-trained Neural Network models with easy-to-access 3D visualizations in a web browser.
By the end of this course, you’ll be able to create compelling 3D visualizations that will show the neural network architecture and how pre-trained models work in real time with TensorSpace
In this course we seamlessly mix the theory with practice, to make your learning experience effective and enjoyable.
What You Will Learn
- Prepare a pre-trained model for visualization from numerous neural network libraries like Keras, TensorFlow and Tensorflow.js.
- Explore how each part of your neural network model is presented and learn how to change it
- Discover the inner-workings of your pre-trained model using a specific example in an easy and accessible way
- Develop new insights by looking at your neural network from a fresh perspective
- Discover how to easily present and explain your neural network architectures.