我正在尝试创建一个基本的编码器-解码器模型来训练聊天机器人。X包含问题或人类对话，Y包含机器人答案。我已经将序列填充到输入和输出句子的最大大小。X.shape =（2363，242，1）和Y.shape =（2363，144，1）。但是在训练过程中，损失对于所有时期都具有值'nan'，并且预测给出所有值都为'nan'的数组。我尝试使用'rmsprop'优化器而不是'亚当'。我不能使用损失函数'categorical_crossentropy'，因为输出不是one-hot编码的，而是一个序列。我的代码到底有什么问题？

型号

model = Sequential()
model.add(LSTM(units=64, activation='relu', input_shape=(X.shape[1], 1)))
model.add(RepeatVector(Y.shape[1]))
model.add(LSTM(units=64, activation='relu', return_sequences=True))
model.add(TimeDistributed(Dense(units=1)))
print(model.summary())

model.compile(optimizer='adam', loss='mean_squared_error')

hist = model.fit(X, Y, epochs=20, batch_size=64, verbose=2)
model.save('encoder_decoder_model_epochs20.h5')

数据准备

def remove_punctuation(s):
    s = s.translate(str.maketrans('','',string.punctuation))
    s = s.encode('ascii', 'ignore').decode('ascii')
    return s

def prepare_data(fname):
    word2idx = {'PAD': 0}
    curr_idx = 1
    sents = list()
    for line in open(fname):
        line = line.strip()
        if line:
            tokens = remove_punctuation(line.lower()).split()
            tmp = []
            for t in tokens:
                if t not in word2idx:
                    word2idx[t] = curr_idx
                    curr_idx += 1
                tmp.append(word2idx[t])
            sents.append(tmp)
    sents = np.array(pad_sequences(sents, padding='post'))
    return sents, word2idx

human = 'rdany-conversations/human_text.txt'
robot = 'rdany-conversations/robot_text.txt'

X, input_vocab = prepare_data(human)
Y, output_vocab = prepare_data(robot)

X = X.reshape((X.shape[0], X.shape[1], 1))
Y = Y.reshape((Y.shape[0], Y.shape[1], 1))