我已经制作了一个 TensorFlow 模型并让训练部分正常工作。模型训练成功，训练时预测准确。不幸的是，当仅使用模型进行预测时，答案大多是胡言乱语，有时甚至是空白。

这是代码：

def train_model():
    loss_track = []
    max_batches = 10001
    batches_in_epoch = 1000
    try:
        for batch in range(max_batches):
            fd = next_feed() # This is a wrapper that prepares the correct response (decoder_targets) and returns batch_method(query_list) (batch method returns encoder_inputs, encoder_input_lenghts)
            _, l_t_a = sess.run([train_op, loss], fd)
            loss_track.append(l_t_a)

            if batch == 0 or batch % batches_in_epoch == 0:
                #fd = random.choice(list(fd))
                #print(fd)
                print('batch {}'.format(batch))
                print('     minibatch loss: {}'.format(sess.run(loss, fd)))
                predict_ = sess.run(decoder_prediction, fd)

                for i, (inp, pred) in enumerate(zip(fd[encoder_inputs].T, predict_.T)):
                    index = random.randint(0, len(fd[encoder_inputs].T)-1)
                    print('     sample {}'.format(i + 1))
                    print('     Query                  > {}'.format(batch_to_words(fd[encoder_inputs].T[index])))
                    print('     Predicted Response     > {}'.format(batch_to_words(predict_.T[index])))
                    if i >= 2:
                        break
                print()
        saver.save(sess, MODEL_LOCATION)
    except KeyboardInterrupt:
        print('Training interrupted.')

def test_model(sentence):
    saver.restore(sess, MODEL_LOCATION)
    batch__ = []
    query = get_formatted_sentence(sentence) # This returns the array of the sentence. ex. ['hello','world']
    batch__.append(
      words_to_batch(query) # This is the inverse of batch_to_words(), it transforms the sentence array in an int array, based on the word vocabulary position
    )
    batch, batch_len = batch_method(batch__)
    prediction = sess.run(decoder_prediction, feed_dict={encoder_inputs: batch, encoder_inputs_length: batch_len})
    batch_response = []
    for i in prediction:
        batch_response.append(i[0])
    print(batch_to_words(batch_response))

这里有什么问题？对于预测部分，我根据需要将查询插入到另一个列表batch_method()中。

请记住，由于某种原因，训练中的预测看起来像这样：（[12,5,3,5,1]这就是我能够batch_to_words()直接调用的原因），而在仅预测模式下，它返回如下内容：（[[3],[4],[64],[23],[1],[0],[1]]这很奇怪）

我也调用train_model()或test_model()单独调用，从不同时运行（这就是我保存模型的原因——与往常一样，我不确定我是否做得正确）。

在这一点上，我不确定这是可以预料的还是我在某个地方搞砸了。

任何帮助表示赞赏。