Question

我对我所制作的模型有一些问题。

1）有时预测会返回一个0的数组（但这可能是正常的）。

2）如果我多次重复预测（使用循环），我总会得到相同的结果。

3）奇怪的是，如果我停止程序并重新运行，预测会发生变化（第2点仍然适用）。

4）结果是错误的。我插入与训练相同的确切查询（训练时预测的响应是正确的），但我的反应非常不同。

现在，奇怪的是，虽然训练我可以看到它正在改善并且它运作良好。

以下是显示正确结果（训练）的代码：

decoder_prediction = tf.argmax(decoder_logits, 2) # This line isn't actually here, I put it here to give context
saver.save(sess, MODEL_LOCATION)
fd = next_feed()
predict_ = sess.run(decoder_prediction, fd) # fd stands for feed_dict. This provides {encoder_inputs: .., encoder_inputs_lenghts: .., decoder_targets: ..}
for i, (inp, pred) in enumerate(zip(fd[encoder_inputs].T, predict_.T)): # This is useless but I did not change it as I dont quite understand it (the zip(fd...) part)
    index = random.randint(0, len(fd[encoder_inputs].T)-1) # This is used to pick a random query/prediction
    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

这是我遇到（预测）问题的部分：

saver.restore(sess, MODEL_LOCATION)
batch__ = []
query = get_formatted_sentence(sentence)
batch__.append(words_to_batch(query))
batch, batch_len = batch_method(batch__)
for x in range(0,10): # This is the loop I was talking about
    prediction = sess.run(decoder_prediction, feed_dict={encoder_inputs: batch, encoder_inputs_length: batch_len}) # Notice that here I do not give decoder_targets ( If I understand them correctly they are the 'wanted' result. In this case I have no 'wanted' result, I just want to get a prediction
    print(prediction.T)
    print(batch_to_words(prediction.T[0]))

那就是它。我不知道为什么会这样。任何帮助表示赞赏。我还包括其他方法以获得更多背景信息。

这是next_feed（）：

def next_feed():

    encoder_inputs_, encoder_input_lengths_ = batch_method(batches_query)
    decoder_targets_, _ = batch_method(
        [sequence + [EOS] + [PAD] for sequence in iter(batches_response)]
    )
    #print(encoder_inputs_)
    #print(encoder_input_lengths_)
    return {
        encoder_inputs: encoder_inputs_,
        encoder_inputs_length: encoder_input_lengths_,
        decoder_targets: decoder_targets_,
    }

这是batch_method：

def batch_method(inputs, max_sequence_length=None):
    """
    Args:
        inputs:
            list of sentences (integer lists)
        max_sequence_length:
            integer specifying how large should `max_time` dimension be.
            If None, maximum sequence length would be used

    Outputs:
        inputs_time_major:
            input sentences transformed into time-major matrix
            (shape [max_time, batch_size]) padded with 0s
        sequence_lengths:
            batch-sized list of integers specifying amount of active
            time steps in each input sequence
    """

    sequence_lengths = [len(seq) for seq in inputs]
    batch_size_ = len(inputs)

    if max_sequence_length is None:
        max_sequence_length = max(sequence_lengths)

    inputs_batch_major = np.zeros(shape=[batch_size_, max_sequence_length], dtype=np.int32)  # == PAD

    for index, seq in enumerate(inputs):
        for j, element in enumerate(seq):
            inputs_batch_major[index, j] = element

    # [batch_size, max_time] -> [max_time, batch_size]
    inputs_time_major = inputs_batch_major.swapaxes(0, 1)

    return inputs_time_major, sequence_lengths

TensorFlow：预测无法正常工作

0 个答案: