Oreilly - 3D Neural Network Visualization with TensorSpace
by Jakub Konczyk | Released March 2019 | ISBN: 9781838642105
Visualize a variety of Neural Network architectures and even show how your pre-trained models process data in real-timeAbout This VideoPrepare pre-trained models from a variety of neural network libraries for 3D visualizationDiscover how to present the architecture of your neural networkExplore ways to show how your pre-trained neural network models work with example data in real-timeIn DetailTensorSpace 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 TensorSpaceThe code bundle for this video course is available at - https://github.com/PacktPublishing/3D-Neural-Network-Visualization-with-TensorSpaceDownloading the example code for this course: You can download the example code files for all Packt video courses you have purchased from your account at http://www.PacktPub.com. If you purchased this course elsewhere, you can visit http://www.PacktPub.com/support and register to have the files e-mailed directly to you. Show and hide more
- Chapter 1 : Introduction to 3D Neural Network Visualization
- The Course Overview 00:02:50
- Why Visualize Your Neural Network Models? 00:03:21
- Getting Ready for Visualizing Your Models 00:02:16
- Chapter 2 : Creating Your First Neural Network Visualization
- Create the Basic Web Page for TensorSpace 00:05:44
- Generate Your First Neural Network Visualization Step-by-Step 00:07:59
- Pre-Process Existing Model for TensorSpace 00:09:02
- Pre-Process Keras MNIST Model for TensorSpace Step-by-Step 00:08:35
- Chapter 3 : Configuring Visualization for Your Neural Network Model
- Default Controls and How to Configure Them 00:04:42
- Changing the Color of a Layer and Animation Speed 00:02:57
- Visualizing Convolution, Pooling Layers 00:02:34
- Visualizing Cropping, Padding, and Sampling Layers 00:01:40
- Visualizing YOLO Grid Layer 00:01:17
- Visualizing Activations, Flattening, and Input-Output Detections Layers 00:02:36
Show and hide more