What's the difference between sequence preprocessing and text preprocessing in Keras?

Question

In Keras, we mainly have three types of preprocessing, i.e., sequence preprocessing, text preprocessing, and image preprocessing. However, for me, I think the meanings of the word "sequence" and "text" are the same. How to understand the differences between these two preprocessing operations?

Answer 1

In tf.keras.preprocessing.text (docs) you have utilities to process discrete token sequences, normally used to represent text.

In tf.keras.preprocessing.sequence (docs) you have utilities to process both continuous value sequences (normally used to represent time series) like TimeSeriesGenerator, and discrete token sequences (i.e. text), like the skipgrams function.