Python 如何拆分数据集并将其与LSTM seq2seq模型一起使用？

我想将数据集拆分为测试和验证数据集，因为我的模型可能会出现过度拟合。以下是我当前的体系结构：

input_sentences = []
output_sentences = []
output_sentences_inputs = []

count = 0
for line in open(r'/content/drive/My Drive/TEMPPP/123.txt', encoding="utf-8"):
    count += 1

    if count > NUM_SENTENCES:
        break

    if '\t' not in line:
        continue

    input_sentence, output = line.rstrip().split('\t')

    output_sentence = output + ' <eos>'
    output_sentence_input = '<sos> ' + output

    input_sentences.append(input_sentence)
    output_sentences.append(output_sentence)
    output_sentences_inputs.append(output_sentence_input)

input_tokenizer = Tokenizer(num_words=MAX_NUM_WORDS)
input_tokenizer.fit_on_texts(input_sentences)
input_integer_seq = input_tokenizer.texts_to_sequences(input_sentences)

word2idx_inputs = input_tokenizer.word_index

max_input_len = max(len(sen) for sen in input_integer_seq)

output_tokenizer = Tokenizer(num_words=MAX_NUM_WORDS, filters='')
output_tokenizer.fit_on_texts(output_sentences + output_sentences_inputs)
output_integer_seq = output_tokenizer.texts_to_sequences(output_sentences)
output_input_integer_seq = output_tokenizer.texts_to_sequences(output_sentences_inputs)

word2idx_outputs = output_tokenizer.word_index

num_words_output = len(word2idx_outputs) + 1
max_out_len = max(len(sen) for sen in output_integer_seq)

encoder_input_sequences = pad_sequences(input_integer_seq, maxlen=max_input_len)
decoder_input_sequences = pad_sequences(output_input_integer_seq, maxlen=max_out_len, padding='post')

import numpy as np
read_dictionary = np.load('/content/drive/My Drive/TEMPPP/hinvec.npy',allow_pickle='TRUE').item()
num_words = min(MAX_NUM_WORDS, len(word2idx_inputs) + 1)
embedding_matrix = np.zeros((num_words, EMBEDDING_SIZE))
for word, index in word2idx_inputs.items():
    embedding_vector = read_dictionary.get(word)
    if embedding_vector is not None:
        embedding_matrix[index] = embedding_vector

embedding_layer = Embedding(num_words, EMBEDDING_SIZE, weights=[embedding_matrix], input_length=max_input_len)

decoder_targets_one_hot = np.zeros((
        len(input_sentences),
        max_out_len,
        num_words_output
    ),
    dtype='float32'
)
decoder_output_sequences = pad_sequences(output_integer_seq, maxlen=max_out_len, padding='post')
for i, d in enumerate(decoder_output_sequences):
    for t, word in enumerate(d):
        decoder_targets_one_hot[i, t, word] = 1

encoder_inputs_placeholder = Input(shape=(max_input_len,))
x = embedding_layer(encoder_inputs_placeholder)
encoder = LSTM(LSTM_NODES, return_state=True)

encoder_outputs, h, c = encoder(x)
encoder_states = [h, c]

decoder_inputs_placeholder = Input(shape=(max_out_len,))

decoder_embedding = Embedding(num_words_output, LSTM_NODES)
decoder_inputs_x = decoder_embedding(decoder_inputs_placeholder)

decoder_lstm = LSTM(LSTM_NODES, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(decoder_inputs_x, initial_state=encoder_states)

decoder_dense = Dense(num_words_output, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)

import tensorflow as tf

starter_learning_rate = 0.1
end_learning_rate = 0.01
decay_steps = 2000
learning_rate_fn = tf.keras.optimizers.schedules.PolynomialDecay(
    starter_learning_rate,
    decay_steps,
    end_learning_rate,
    power=0.5)

opt = tf.keras.optimizers.Adam(learning_rate=learning_rate_fn, epsilon=1e-03, clipvalue=0.5)

model = Model([encoder_inputs_placeholder,
  decoder_inputs_placeholder],
  decoder_outputs)
model.compile(
    optimizer=opt,
    loss='categorical_crossentropy',
    metrics=['accuracy']
)

history = model.fit(
    [encoder_input_sequences, decoder_input_sequences],
    decoder_targets_one_hot,
    batch_size=BATCH_SIZE,
    epochs=EPOCHS,
    validation_split=0.1,
)

通过这种方式，我可以用X表示我的印地语句子，用y表示我的英语句子。现在我真的很困惑如何在我的模型中实现它

from sklearn.model_selection import train_test_split

X=input_sentences
y=output_sentences

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)