List of Listings

 

Chapter 2. TensorFlow essentials

Listing 2.1. Computing the inner product of two vectors without using a library

Listing 2.2. Computing the inner product using NumPy

Listing 2.3. Different ways to represent tensors

Listing 2.4. Creating tensors

Listing 2.5. Using the negation operator

Listing 2.6. Using a session

Listing 2.7. Using the interactive session mode

Listing 2.8. Logging a session

Listing 2.9. Using a variable

Listing 2.10. Saving variables

Listing 2.11. Loading variables

Listing 2.12. Defining the average update operator

Listing 2.13. Running iterations of the exponential average algorithm

Listing 2.14. Filling in missing code to complete the exponential average algorithm

Listing 2.15. Annotating with a summary op

Listing 2.16. Writing summaries to view in TensorBoard

Chapter 3. Linear regression and beyond

Listing 3.1. Visualizing raw input

Listing 3.2. Solving linear regression

Listing 3.3. cost functionUsing a polynomial model

Listing 3.4. Splitting the dataset into testing and training sets

Listing 3.5. Evaluating regularization parameters

Listing 3.6. Parsing raw CSV datasets

Chapter 4. A gentle introduction to classification

Listing 4.1. Using linear regression for classification

Listing 4.2. Executing the graph

Listing 4.3. Measuring accuracy

Listing 4.4. Linear regression failing miserably for classification

Listing 4.5. Using one-dimensional logistic regression

Listing 4.6. Setting up data for two-dimensional logistic regression