TensorFlow is a popular library for implementing machine learning-based solutions. It includes a low-level API known as TensorFlow core and many high-level APIs, including two of the most popular ones, known as TensorFlow Estimators and Keras. In this chapter, we will learn about the basics of TensorFlow and build a machine learning model using logistic regression to classify handwritten digits as an example.
We will cover the following topics in this chapter:
- TensorFlow core:
- Tensors in TensorFlow core
- Constants
- Placeholders
- Operations
- Tensors from Python objects
- Variables
- Tensors from library functions
- Computation graphs:
- Lazy loading and execution order
- Graphs on multiple devices – CPU and GPGPU
- Working with multiple graphs
- Machine learning, classification, and logistic regression
- Logistic regression examples in TensorFlow
- Logistic regression examples in Keras
You can follow the code examples in this chapter by using the Jupyter Notebook named ch-01_Overview_of_TensorFlow_and_Machine_Learning.ipynb that's included in the code bundle.
