2 TensorFlow 2.0

 

This chapter covers,

  • What is TensorFlow, main differences between TensorFlow 1 and TensorFlow 2 and great features of TensorFlow 2 such as AutoGraph and Eager Exectution
  • Various data structures and operations in TensorFlow such as, tf.Variable and tf.Tensor
  • Common neural network related operations in TensorFlow

In the previous chapter we learned that TensorFlow is an end-to-end machine learning framework predominantly used for implementing deep neural networks. TensorFlow is skillful at converting these deep neural networks to computational graphs that run faster on optimized hardware (e.g. Graphical Processing Units - GPUs and Tensor Processing Units - TPUs). But keep in mind that this is not the only use for TensorFlow. Table 2.1 delineates other areas TensorFlow supports.

2.1      TensorFlow 1.0 vs TensorFlow 2.0

2.1.1   How does TensorFlow operate under the hood?

2.1.2   Visiting an old friend: TensorFlow 1

2.2      TensorFlow building-blocks

2.2.1   Understanding tf.Variable

2.2.2   Understanding tf.Tensor

2.2.3   Understanding tf.Operation

2.3      Neural network related computations in TensorFlow

2.3.1   Matrix multiplication

2.3.2   Convolution operation

2.3.3   Pooling operation

2.4      Summary

2.5      Answers to exercises