datasets.py 文件源码

def load_imdb():
    from keras.preprocessing.text import Tokenizer
    from keras.datasets import imdb
    max_words = 1000

    print('Loading data...')
    (x1, y1), (x2, y2) = imdb.load_data(num_words=max_words)
    x = np.concatenate((x1, x2))
    y = np.concatenate((y1, y2))
    print(len(x), 'train sequences')

    num_classes = np.max(y) + 1
    print(num_classes, 'classes')

    print('Vectorizing sequence data...')
    tokenizer = Tokenizer(num_words=max_words)
    x = tokenizer.sequences_to_matrix(x, mode='binary')
    print('x_train shape:', x.shape)

    return x.astype(float), y