Using the Keras Preprocessing API

The Keras Preprocessing API gathers modules for data processing and data augmentation. This API provides utilities for working with sequence, text, and image data. Data preprocessing is an essential step in machine learning and deep learning. It converts, transforms, or encodes raw data into an understandable, useful, and efficient format for learning algorithms.

Getting ready

This recipe will cover some preprocessing methods provided by Keras for sequence, text, and image data.

As usual, we just need to import TensorFlow as follows:

import tensorflow as tf
from tensorflow import keras
import numpy as np
from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator, pad_sequences, skipgrams, make_sampling_table
from tensorflow.keras.preprocessing.text import text_to_word_sequence, one_hot, hashing_trick, Tokenizer
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

We are ready to...