python - Tensorflow 下一个词预测器错误

Question

我有以下代码

 flags = tf.flags
logging = tf.logging

flags.DEFINE_string('model', 'small',
                    'A type of model. Possible options are: small, medium, large.'
                    )
flags.DEFINE_string('data_path', None, 'data_path')
flags.DEFINE_string('checkpoint_dir', 'ckpt', 'checkpoint_dir')
flags.DEFINE_bool('use_fp16', False,
                'Train using 16-bit floats instead of 32bit floats')
flags.DEFINE_bool('train', False, 'should we train or test')

FLAGS = flags.FLAGS


def data_type():
    return tf.float16 if FLAGS.use_fp16 else tf.float32


class PTBModel(object):
    """The PTB model."""

    def __init__(self, is_training, config):
        self.batch_size = batch_size = config.batch_size
        self.num_steps = num_steps = config.num_steps
        size = config.hidden_size
        vocab_size = config.vocab_size

        self._input_data = tf.placeholder(tf.float32, [batch_size,
                                                    num_steps])
        self._targets = tf.placeholder(tf.int32, [batch_size,
                                                num_steps])

        # Slightly better results can be obtained with forget gate biases
        # initialized to 1 but the hyperparameters of the model would need to be
        # different than reported in the paper.

        lstm_cell = tf.nn.rnn_cell.BasicLSTMCell(size, forget_bias=0.0,
                                                state_is_tuple=True)
        if is_training and config.keep_prob < 1:
            lstm_cell = tf.nn.rnn_cell.DropoutWrapper(lstm_cell,
                                                    output_keep_prob=config.keep_prob)
        cell = tf.nn.rnn_cell.MultiRNNCell([lstm_cell]
                                        * config.num_layers, state_is_tuple=True)

        self._initial_state = cell.zero_state(batch_size, data_type())

        with tf.device('/cpu:0'):
            embedding = tf.get_variable('embedding', [vocab_size,
                                                    size], dtype=data_type())
            inputs = tf.nn.embedding_lookup(embedding, self._input_data)

        if is_training and config.keep_prob < 1:
            inputs = tf.nn.dropout(inputs, config.keep_prob)

            # Simplified version of tensorflow.models.rnn.rnn.py's rnn().
            # This builds an unrolled LSTM for tutorial purposes only.
            # In general, use the rnn() or state_saving_rnn() from rnn.py.
            #
            # The alternative version of the code below is:
            #
            # from tensorflow.models.rnn import rnn

        inputs = [tf.squeeze(input_, [1]) for input_ in tf.split(inputs, num_steps, axis=1)]

        (outputs, state) = tf.nn.rnn(cell, inputs, initial_state=self._initial_state)

        # outputs = []
        # state = self._initial_state
        # with tf.variable_scope("RNN"):
        #  for time_step in range(num_steps):
        #    if time_step > 0: tf.get_variable_scope().reuse_variables()
        #    (cell_output, state) = cell(inputs[:, time_step, :], state)
        #    outputs.append(cell_output)

        output = tf.reshape(tf.concat(outputs, axis=1), [-1, size])
        softmax_w = tf.get_variable('softmax_w', [size, vocab_size],
                                    dtype=data_type())
        softmax_b = tf.get_variable('softmax_b', [vocab_size],
                                    dtype=data_type())
        logits = tf.matmul(output, softmax_w) + softmax_b

        loss = tf.nn.seq2seq.sequence_loss_by_example([logits],
                                                    [tf.reshape(self._targets, [-1])], [tf.ones([batch_size
                                                                                                * num_steps],
                                                                                                dtype=data_type())])
        self._cost = cost = tf.reduce_sum(loss) / batch_size
        self._final_state = state

        # RANI

        self.logits = logits

        if not is_training:
            return

        self._lr = tf.Variable(0.0, trainable=False)
        tvars = tf.trainable_variables()
        (grads, _) = tf.clip_by_global_norm(tf.gradients(cost, tvars),
                                            config.max_grad_norm)
        optimizer = tf.train.GradientDescentOptimizer(self._lr)
        self._train_op = optimizer.apply_gradients(zip(grads, tvars))

        self._new_lr = tf.placeholder(tf.float32, shape=[],
                                    name='new_learning_rate')
        self._lr_update = tf.assign(self._lr, self._new_lr)

    def assign_lr(self, session, lr_value):
        session.run(self._lr_update, feed_dict={self._new_lr: lr_value})


    ...

但是，当我运行它时，出现以下错误

File "ptb_word_lm.py", line 349, in <module>
    tf.app.run()
File "C:\Users\Josh Goldman\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\platform\app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "ptb_word_lm.py", line 299, in main
    m = PTBModel(is_training=True, config=config)
File "ptb_word_lm.py", line 60, in __init__
    inputs = tf.nn.embedding_lookup(embedding, self._input_data)
File "C:\Users\Josh Goldman\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\embedding_ops.py", line 122, in embedding_lookup
    return maybe_normalize(_do_gather(params[0], ids, name=name))
File "C:\Users\Josh Goldman\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\embedding_ops.py", line 42, in _do_gather
    return array_ops.gather(params, ids, name=name)
File "C:\Users\Josh Goldman\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 1179, in gather
    validate_indices=validate_indices, name=name)
File "C:\Users\Josh Goldman\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 589, in apply_op
    param_name=input_name)
File "C:\Users\Josh Goldman\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 60, in _SatisfiesTypeConstraint
    ", ".join(dtypes.as_dtype(x).name for x in allowed_list)))
TypeError: Value passed to parameter 'indices' has DataType float32 not in list of allowed values: int32, int64

有人，请帮助我。我已将所有软件包升级到最新版本。我正在使用正确的解释器。如果错误很简单，我很抱歉。我只有 13 岁，对编程还很陌生。顺便说一句，这段代码不是我的；我是从 Github 上得到的。

Answer 1

错误是由于 tensorflow 版本，tf.split 的语法在新版本中发生了变化。 tf.concat

还有另一个同样的问题

# replace this line with the following one
inputs = [tf.squeeze(input_, [1]) for input_ in tf.split(1, num_steps, inputs)]
# this support `tensorflow >= 1.0.0`
inputs = [tf.squeeze(input_, [1]) for input_ in tf.split(inputs, num_steps, axis=1)]

# Also use dtype float32 for inputs
self._input_data = tf.placeholder(tf.float32, [batch_size,
                                                 num_steps])

# replace this line
output = tf.reshape(tf.concat(1, outputs), [-1, size])
# with this one
output = tf.reshape(tf.concat(outputs, axis=1), [-1, size])