Gibberish Keras LSTM DeepSpell выходной

Question

Я пытаюсь создать корректор орфографии на основе LSTM после этого блога. Хорошо работает во время тренировки. Обратитесь к приложенному скриншоту. ,

Я сделал небольшие изменения, чтобы вводимые слова были неверными, в основном, именами, такими как имя, и постараюсь дать подсказку. Я правильно сделал векторизацию текста, но все равно получаю бессмысленный вывод из LSTM. Вот файлы моделей после 11 эпох.

Вот мой модуль Python

import numpy as np
from numpy import zeros as np_zeros
from keras.models import model_from_json

seed = 7
np.random.seed(seed)

class CharacterTable(object):
    """
    Given a set of characters:
    + Encode them to a one hot integer representation
    + Decode the one hot integer representation to their character output
    + Decode a vector of probabilities to their character output
    """

    def __init__(self, chars):
        self.chars = sorted(set(chars))
        self.char_indices = dict((c, i) for i, c in enumerate(self.chars))
        self.indices_char = dict((i, c) for i, c in enumerate(self.chars))
        self.size = len(self.chars)

    def encode(self, C, maxlen):
        """Encode as one-hot"""
        X = np_zeros((maxlen, len(self.chars)), dtype=np.bool)  # pylint:disable=no-member
        for i, c in enumerate(C):
            X[i, self.char_indices[c]] = 1
        return X

    def decode(self, X, calc_argmax=True):
        """Decode from one-hot"""
        if calc_argmax:
            X = X.argmax(axis=-1)
        return ''.join(self.indices_char[x] for x in X)


def load_saved_model(checkpoint_filename=None,dataset_params_filename=None):
#         # serialize model to JSON

    # load json and create model

    json_file = open('/deepspell/models_gpu_1/model_gpu_1.json','r')

    loaded_model_json = json_file.read()
    json_file.close()
    model = model_from_json(loaded_model_json)
    print("Loaded Model")

    if checkpoint_filename is not None:
        model.load_weights(checkpoint_filename)
        print("Loaded Model Weights")

    return model

def vectorize(questions):
    """Vectorize the questions list and expected answers list"""
    # Samples, Time steps, features
    X = np_zeros((len(questions), x_max_length, character_table.size), dtype=np.bool)

    for i in range(len(questions)):
        sentence = questions[i]
        for j, c in enumerate(sentence):
            X[i, j, character_table.char_indices[c]] = 1
    return X

def run_autocorrect_name(text):
    """
        text : text to auto-correct
    """
    temp_list = []; temp_list.append(text)
    text_vect = vectorize(temp_list)
    pred_text = model.predict_classes(text_vect,verbose=0)
    suggestion = character_table.decode(pred_text[0], calc_argmax=False)
    print("Suggestion for {} : {} ".format(text,suggestion))
    return suggestion

CHARS = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ .")
# chars_answer : list of lowercase A-Z, dot, dash, space
# chars_question : list of lowercase + uppercase A-Z, dot, dash, space
chars_answer = {'k', '.', 'x', 'l', 'n', 't', 'p', 'm', 'b', 'r', 'e', 'i', 'g', 'y', 'z', 'u', 'f', 'q', 'o', 's', 'd', 'j', ' ', 'v', 'h', 'a', '-', 'c', 'w'}
chars_question = {'I', 'k', '.', 'x', 'l', 'n', 'Q', 't', 'm', 'p', 'b', 'r', 'e', 'i', 'K', 'S', 'g', 'H', 'M', 'y', 'z', 'u', 'W', 'R', 'L', 'U', 'f', 'q', 'X', 'G', 'F', 'Y', 'A', 'T', 'o', 'J', 's', 'Z', 'd', 'j', 'D', 'O', ' ', 'v', 'V', 'C', 'h', 'E', 'N', 'B', 'a', '-', 'P', 'c', 'w'}
chars = sorted(list(set.union(chars_answer, chars_question)))    
x_max_length = 40
character_table = CharacterTable(chars)
# load weights
model = '/deepspell/models_gpu_1/weights.11-0.11.hdf5' # 11 epoch
# load the model
model = load_saved_model(checkpoint_filename=model)
# Compile model (required to make predictions)
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

test_str = 'Taylor Swift'
run_autocorrect_name(test_str)

Результатом вышесказанного является

Suggestion for Taylor Swift : anezalrr  gilluuhhooooosssaaa...........