Oreilly – TensorFlow in Action, Video Edition 2022-10

Apr 18, 2025 - 18:58

0 0

TensorFlow in Action, Video Edition. This course teaches you the secrets of designing with TensorFlow to build successful deep learning applications. In this hands-on guide, Thushan Ganegedara, an active StackOverflow contributor on deep learning, walks you through the new features of TensorFlow 2. In this course, you’ll not only master the fundamentals of TensorFlow, but also learn how to implement deep learning networks, choose a high-level Keras API for model building, write end-to-end data pipelines, build models for computer vision and natural language processing, use pre-trained NLP models, and get acquainted with new algorithms like transformers, attention models, and ElMo.

What you will learn:

TensorFlow Basics
Implementing deep learning networks
Choosing the high-level Keras API for model building
Writing end-to-end data pipelines
Building models for computer vision and natural language processing
Using pre-trained NLP models
New algorithms such as transformers, attention models, and ElMo

Who is this course suitable for?

This course is suitable for Python programmers with basic deep learning skills.

TensorFlow in Action, Video Edition Course Specifications

Publisher: Oreilly
Instructor: Thushan Ganegedara
Training level: Beginner to advanced
Training duration: 18 hours and 8 minutes

Course headings

Part 1. Foundations of TensorFlow 2 and deep learning
Chapter 1. The amazing world of TensorFlow
Chapter 1. GPU vs. CPU
Chapter 1. When and when not to use TensorFlow
Chapter 1. What will this book teach you?
Chapter 1. Who is this book for?
Chapter 1. Should we really care about Python and TensorFlow 2?
Chapter 1. Summary
Chapter 2. TensorFlow 2
Chapter 2. TensorFlow building blocks
Chapter 2. Neural network-related computations in TensorFlow
Chapter 2. Summary
Chapter 3. Keras and data retrieval in TensorFlow 2
Chapter 3. Retrieving data for TensorFlow/Keras models
Chapter 3. Summary
Chapter 4. Dipping toes in deep learning
Chapter 4. Convolutional neural networks
Chapter 4. One step at a time: Recurrent neural networks (RNNs)
Chapter 4. Summary
Chapter 5. State-of-the-art in deep learning: Transformers
Chapter 5. Understanding the Transformer model
Chapter 5. Summary
Part 2. Look ma, no hands! Deep networks in the real world
Chapter 6. Teaching machines to see: Image classification with CNNs
Chapter 6. Creating data pipelines using the Keras ImageDataGenerator
Chapter 6. Inception net: Implementing a state-of-the-art image classifier
Chapter 6. Training the model and evaluating performance
Chapter 6. Summary
Chapter 7. Teaching machines to see better: Improving CNNs and making them confess
Chapter 7. Toward minimalism: Minception instead of Inception
Chapter 7. If you can’t beat them, join ’em: Using pretrained networks for enhancing performance
Chapter 7. Grad-CAM: Making CNNs confess
Chapter 7. Summary
Chapter 8. Telling things apart: Image segmentation
Chapter 8. Getting serious: Defining a TensorFlow data pipeline
Chapter 8. DeepLabv3: Using pretrained networks to segment images
Chapter 8. Compiling the model: Loss functions and evaluation metrics in image segmentation
Chapter 8. Training the model
Chapter 8. Evaluating the model
Chapter 8. Summary
Chapter 9. Natural language processing with TensorFlow: Sentiment analysis
Chapter 9. Getting text ready for the model
Chapter 9. Defining an end-to-end NLP pipeline with TensorFlow
Chapter 9. Happy reviews mean happy customers: Sentiment analysis
Chapter 9. Training and evaluating the model
Chapter 9. Injecting semantics with word vectors
Chapter 9. Summary
Chapter 10. Natural language processing with TensorFlow: Language modeling
Chapter 10. GRUs in Wonderland: Generating text with deep learning
Chapter 10. Measuring the quality of the generated text
Chapter 10. Training and evaluating the language model
Chapter 10. Generating new text from the language model: Greedy decoding
Chapter 10. Beam search: Enhancing the predictive power of sequential models
Chapter 10. Summary
Part 3. Advanced deep networks for complex problems
Chapter 11. Sequence-to-sequence learning: Part 1
Chapter 11. Writing an English-German seq2seq machine translator
Chapter 11. Training and evaluating the model
Chapter 11. From training to inference: Defining the inference model
Chapter 11. Summary
Chapter 12. Sequence-to-sequence learning: Part 2
Chapter 12. Visualizing the attention
Chapter 12. Summary
Chapter 13. Transformers
Chapter 13. Using pretrained BERT for spam classification
Chapter 13. Question answering with Hugging Face’s Transformers
Chapter 13. Summary
Chapter 14. TensorBoard: Big brother of TensorFlow
Chapter 14. Tracking and monitoring models with TensorBoard
Chapter 14. Using tf.summary to write custom metrics during model training
Chapter 14. Profiling models to detect performance bottlenecks
Chapter 14. Visualizing word vectors with the TensorBoard
Chapter 14. Summary
Chapter 15. TFX: MLOps and deploying models with TensorFlow
Chapter 15. Training a simple regression neural network: TFX Trainer API
Chapter 15. Setting up Docker to serve a trained model
Chapter 15. Deploying the model and serving it through an API
Chapter 15. Summary
Appendix A. Setting up the environment
Appendix A. In Windows Environments
Appendix A. Activating and deactivating the conda environment
Appendix A. Running the Jupyter Notebook server and creating notebooks
Appendix A. Miscellaneous notes
Appendix B. Computer vision
Appendix B. Image segmentation: U-Net model
Appendix C. Natural language processing