Tensorflow下一个单词预测错误

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}) 


    ... 

然而，当我运行它，我得到以下错误

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，请帮帮我。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。如果错误非常简单，我很抱歉。我只有13岁，并且对编程非常新颖。顺便说一句，这个代码不是我的;我从Github那里得到了它。

Answer 1

错误归因于tensorflow版本，tf.split的语法在新版本中发生更改。还有另一个相同的问题tf.concat

# 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])