How do I preprocess data for TensorFlow Keras?

How do I preprocess data for TensorFlow Keras?

To preprocess data for TensorFlow Keras, you can use the ImageDataGenerator for images or StandardScaler for numerical data.

Can you show me an example of using ImageDataGenerator?

Sure! Here's a simple example:

from tensorflow.keras.preprocessing.image import ImageDataGenerator

generator = ImageDataGenerator(rescale=1./255)
train_data = generator.flow_from_directory('data/train', target_size=(150, 150), class_mode='binary')

What about preprocessing text data?

For text data, you can use the Tokenizer class to convert text to sequences and pad them using pad_sequences.

Can you provide a code snippet for text preprocessing?

Absolutely! Here's a quick example:

from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences

texts = ['I love TensorFlow', 'Keras is great']
tokenizer = Tokenizer()
tokenizer.fit_on_texts(texts)
sequences = tokenizer.texts_to_sequences(texts)
padded_sequences = pad_sequences(sequences)