keras-preprocessing

import numpy as np import pandas as pd import os # Create dummy image files and a dataframe if not os.path.exists('data/img_dir/cat'): os.makedirs('data/img_dir/cat') if not os.path.exists('data/img_dir/dog'): os.makedirs('data/img_dir/dog') # Create dummy image files from PIL import Image img = Image.new('RGB', (64, 64), color = 'red') img.save('data/img_dir/cat/cat1.jpg') img = Image.new('RGB', (64, 64), color = 'blue') img.save('data/img_dir/dog/dog1.jpg') df = pd.DataFrame({ 'filename': ['cat/cat1.jpg', 'dog/dog1.jpg'], 'class': ['cat', 'dog'] }) from keras_preprocessing.image import ImageDataGenerator from keras_preprocessing.text import Tokenizer from keras_preprocessing.sequence import pad_sequences # Image Preprocessing and Augmentation datagen = ImageDataGenerator( rescale=1./255, rotation_range=20, width_shift_range=0.2, height_shift_range=0.2, horizontal_flip=True ) # Using flow_from_dataframe (requires pandas) image_generator = datagen.flow_from_dataframe( dataframe=df, directory='data/img_dir', x_col='filename', y_col='class', target_size=(64, 64), batch_size=1, class_mode='categorical' ) print(f"First batch of images shape: {next(image_generator)[0].shape}") # Text Preprocessing sentences = [ "This is a sample sentence", "Another example sentence here", "Keras preprocessing is useful" ] tokenizer = Tokenizer(num_words=10, oov_token="<OOV>") tokenizer.fit_on_texts(sentences) sequences = tokenizer.texts_to_sequences(sentences) print(f"Original sequences: {sequences}") # Sequence Padding padded_sequences = pad_sequences(sequences, maxlen=5, padding='post') print(f"Padded sequences: {padded_sequences}") # Cleanup dummy directories (optional) import shutil shutil.rmtree('data', ignore_errors=True)