Video description
Build better PyTorch models with TensorBoard visualization
About This Video
- Learn everything you need to know to start using TensorBoard in PyTorch with practical examples in Machine Learning, Image Classification, and Natural Language Processing (NLP)
- Launch TensorBoard from any developer environment, including Jupyter notebooks and Google Colab
- Visualize and optimize your PyTorch models using techniques such as model graphs, training curves, image data, text embeddings, and many more
In Detail
TensorBoard is a visualization library for TensorFlow that plots training runs, tensors, and graphs. TensorBoard has been natively supported since the PyTorch 1.1 release. In this course, you will learn how to perform Machine Learning visualization in PyTorch via TensorBoard. This course is full of practical, hands-on examples. You will begin with a quick introduction to TensorBoard and how it is used to plot your PyTorch training models. You will learn how to write TensorBoard events and run TensorBoard with PyTorch to obtain visualizations of the training progress of a neural network. You will visualize scalar values, images, text and more, and save them as events. You will log events in PyTorch–for example, scalar, image, audio, histogram, text, embedding, and back-propagation.
By the end of the course, you will be confident enough to use TensorBoard visualizations in PyTorch for your real-world projects.
Publisher resources
Table of contents
-
Chapter 1 : Introduction to TensorBoard
- Course Overview 00:05:06
- What Is TensorBoard and How Do We Leverage Its Power 00:05:48
- Running TensorBoard with PyTorch 00:05:13
- Running TensorBoard on Jupyter Notebooks and Google Colab 00:06:55
-
Chapter 2 : Your First PyTorch Model with TensorBoard
- Simple Regression Example 00:02:26
- Visualizing Your Model Graph 00:05:13
- Training and Visualizing Loss Using TensorBoard 00:05:50
- Visualizing Data Summaries and Histograms 00:05:46
- Visualizing Other Data Types 00:04:25
-
Chapter 3 : Image Classification and Model Development
- Hands-On Example: Image Classification 00:02:42
- Detect and Fix Errors with Model Graph Visualizations 00:09:05
- Visualize Training Loss and Other Metrics 00:03:20
- Visualize Image Data 00:03:36
- Display Confusion Matrix Using TensorBoard 00:03:16
-
Chapter 4 : NLP Visualization and Model Experimentation
- Hands-On Example: NLP 00:06:38
- Visualizing Text Data 00:07:45
- Visualizing Word Embedding Using TensorBoard Projector 00:13:35
- Visualizing Model Graph - RNN 00:06:04
- Advanced Features and Limitations 00:15:48
- Advanced Features of TensorBoard and PyTorch Limitations 00:03:32
-
Chapter 5 : Reviewing Your Visualizations and Models
- Visualizations Review 00:02:56
- Model Development Review 00:05:03
- What to do Next? 00:02:57
Product information
- Title: Hands-On TensorBoard for PyTorch Developers
- Author(s):
- Release date: March 2020
- Publisher(s): Packt Publishing
- ISBN: 9781838983604
You might also like
book
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition
Through a series of recent breakthroughs, deep learning has boosted the entire field of machine learning. …
book
40 Algorithms Every Programmer Should Know
Learn algorithms for solving classic computer science problems with this concise guide covering everything from fundamental …
video
Python Fundamentals
51+ hours of video instruction. Overview The professional programmer’s Deitel® video guide to Python development with …
video
Machine Learning Projects with TensorFlow 2.0
Build and train models for real-world machine learning projects using Tensorflow 2.0 About This Video Make …
