Tensorflow seq2seq tutorial: NoneType object has no 'update' attribute

I am trying to follow tensorflow tutorial from https://www.tensorflow.org/tutorials/seq2seq .

The data seems to be loading fine, but when I initialize the model I get the following error:

Traceback (most recent call last):
  File "/Users/<username>/PycharmProjects/tensorflow_chatbot/execute.py", line 334, in <module>
    train()
  File "/Users/<username>/PycharmProjects/tensorflow_chatbot/execute.py", line 151, in train
    model = create_model(sess, False)
  File "/Users/<username>/PycharmProjects/tensorflow_chatbot/execute.py", line 113, in create_model
    forward_only=forward_only)
  File "/Users/<username>/PycharmProjects/tensorflow_chatbot/seq2seq_model_tf.py", line 181, in __init__
    softmax_loss_function=softmax_loss_function)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/site-packages/tensorflow/contrib/legacy_seq2seq/python/ops/seq2seq.py", line 1206, in model_with_buckets
    decoder_inputs[:bucket[1]])
  File "/Users/<username>/PycharmProjects/tensorflow_chatbot/seq2seq_model_tf.py", line 180, in <lambda>
    lambda x, y: seq2seq_f(x, y, False),
  File "/Users/<username>/PycharmProjects/tensorflow_chatbot/seq2seq_model_tf.py", line 144, in seq2seq_f
    dtype=dtype)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/site-packages/tensorflow/contrib/legacy_seq2seq/python/ops/seq2seq.py", line 848, in embedding_attention_seq2seq
    encoder_cell = copy.deepcopy(cell)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 174, in deepcopy
    y = copier(memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/site-packages/tensorflow/python/layers/base.py", line 476, in __deepcopy__
    setattr(result, k, copy.deepcopy(v, memo))
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 163, in deepcopy
    y = copier(x, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 230, in _deepcopy_list
    y.append(deepcopy(a, memo))
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 190, in deepcopy
    y = _reconstruct(x, rv, 1, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 334, in _reconstruct
    state = deepcopy(state, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 163, in deepcopy
    y = copier(x, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 257, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 190, in deepcopy
    y = _reconstruct(x, rv, 1, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 334, in _reconstruct
    state = deepcopy(state, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 163, in deepcopy
    y = copier(x, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 257, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 190, in deepcopy
    y = _reconstruct(x, rv, 1, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 334, in _reconstruct
    state = deepcopy(state, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 163, in deepcopy
    y = copier(x, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 257, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 190, in deepcopy
    y = _reconstruct(x, rv, 1, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 334, in _reconstruct
    state = deepcopy(state, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 163, in deepcopy
    y = copier(x, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 257, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 163, in deepcopy
    y = copier(x, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 257, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 163, in deepcopy
    y = copier(x, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 230, in _deepcopy_list
    y.append(deepcopy(a, memo))
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 190, in deepcopy
    y = _reconstruct(x, rv, 1, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 334, in _reconstruct
    state = deepcopy(state, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 163, in deepcopy
    y = copier(x, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 257, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 190, in deepcopy
    y = _reconstruct(x, rv, 1, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 334, in _reconstruct
    state = deepcopy(state, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 163, in deepcopy
    y = copier(x, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 257, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 190, in deepcopy
    y = _reconstruct(x, rv, 1, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 334, in _reconstruct
    state = deepcopy(state, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 163, in deepcopy
    y = copier(x, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 257, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 163, in deepcopy
    y = copier(x, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 230, in _deepcopy_list
    y.append(deepcopy(a, memo))
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 163, in deepcopy
    y = copier(x, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 237, in _deepcopy_tuple
    y.append(deepcopy(a, memo))
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 163, in deepcopy
    y = copier(x, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 257, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 190, in deepcopy
    y = _reconstruct(x, rv, 1, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 334, in _reconstruct
    state = deepcopy(state, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 163, in deepcopy
    y = copier(x, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 257, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 190, in deepcopy
    y = _reconstruct(x, rv, 1, memo)
  File "/Users/<username>/anaconda/envs/tensorflow_source_gpu/lib/python2.7/copy.py", line 343, in _reconstruct
    y.__dict__.update(state)
AttributeError: 'NoneType' object has no attribute 'update'

      

        
        
        
      

    

If I change the variable _buckets

in translate.py

to only have 1 tuple (it doesn't matter which one), no problem, but the training doesn't work very well. This error causes at most 1 tuple. No changes were made to the files found on github at https://github.com/tensorflow/models/tree/master/tutorials/rnn/translate other than changing the filenames for my local project.

The beginning of the function __init__

leading to the area looks like this:

def __init__(self,
             source_vocab_size,
             target_vocab_size,
             buckets,
             size,
             num_layers,
             max_gradient_norm,
             batch_size,
             learning_rate,
             learning_rate_decay_factor,
             use_lstm=False,
             num_samples=512,
             forward_only=False,
             dtype=tf.float32):
    """Create the model.

Args:
  source_vocab_size: size of the source vocabulary.
  target_vocab_size: size of the target vocabulary.
  buckets: a list of pairs (I, O), where I specifies maximum input length
    that will be processed in that bucket, and O specifies maximum output
    length. Training instances that have inputs longer than I or outputs
    longer than O will be pushed to the next bucket and padded accordingly.
    We assume that the list is sorted, e.g., [(2, 4), (8, 16)].
  size: number of units in each layer of the model.
  num_layers: number of layers in the model.
  max_gradient_norm: gradients will be clipped to maximally this norm.
  batch_size: the size of the batches used during training;
    the model construction is independent of batch_size, so it can be
    changed after initialization if this is convenient, e.g., for decoding.
  learning_rate: learning rate to start with.
  learning_rate_decay_factor: decay learning rate by this much when needed.
  use_lstm: if true, we use LSTM cells instead of GRU cells.
  num_samples: number of samples for sampled softmax.
  forward_only: if set, we do not construct the backward pass in the model.
  dtype: the data type to use to store internal variables.
"""
    self.source_vocab_size = source_vocab_size
    self.target_vocab_size = target_vocab_size
    self.buckets = buckets
    self.batch_size = batch_size
    self.learning_rate = tf.Variable(
        float(learning_rate), trainable=False, dtype=dtype)
    self.learning_rate_decay_op = self.learning_rate.assign(
        self.learning_rate * learning_rate_decay_factor)
    self.global_step = tf.Variable(0, trainable=False)

    # If we use sampled softmax, we need an output projection.
    output_projection = None
    softmax_loss_function = None
    # Sampled softmax only makes sense if we sample less than vocabulary size.
    if 0 < num_samples < self.target_vocab_size:
        w_t = tf.get_variable("proj_w", [self.target_vocab_size, size], dtype=dtype)
        w = tf.transpose(w_t)
        b = tf.get_variable("proj_b", [self.target_vocab_size], dtype=dtype)
        output_projection = (w, b)

        def sampled_loss(labels, logits):
            labels = tf.reshape(labels, [-1, 1])
            # We need to compute the sampled_softmax_loss using 32bit floats to
            # avoid numerical instabilities.
            local_w_t = tf.cast(w_t, tf.float32)
            local_b = tf.cast(b, tf.float32)
            local_inputs = tf.cast(logits, tf.float32)
            return tf.cast(
                tf.nn.sampled_softmax_loss(
                    weights=local_w_t,
                    biases=local_b,
                    labels=labels,
                    inputs=local_inputs,
                    num_sampled=num_samples,
                    num_classes=self.target_vocab_size),
                dtype)

        softmax_loss_function = sampled_loss

    # Create the internal multi-layer cell for our RNN.
    def single_cell():
        return tf.contrib.rnn.GRUCell(size)

    if use_lstm:
        def single_cell():
            return tf.contrib.rnn.BasicLSTMCell(size)
    cell = single_cell()
    if num_layers > 1:
        cell = tf.contrib.rnn.MultiRNNCell([single_cell() for _ in range(num_layers)])

    # The seq2seq function: we use embedding for the input and attention.
    def seq2seq_f(encoder_inputs, decoder_inputs, do_decode):
        return tf.contrib.legacy_seq2seq.embedding_attention_seq2seq(
            encoder_inputs,
            decoder_inputs,
            cell,
            num_encoder_symbols=source_vocab_size,
            num_decoder_symbols=target_vocab_size,
            embedding_size=size,
            output_projection=output_projection,
            feed_previous=do_decode,
            dtype=dtype)

    # Feeds for inputs.
    self.encoder_inputs = []
    self.decoder_inputs = []
    self.target_weights = []
    for i in xrange(buckets[-1][0]):  # Last bucket is the biggest one.
        self.encoder_inputs.append(tf.placeholder(tf.int32, shape=[None],
                                                  name="encoder{0}".format(i)))
    for i in xrange(buckets[-1][1] + 1):
        self.decoder_inputs.append(tf.placeholder(tf.int32, shape=[None],
                                                  name="decoder{0}".format(i)))
        self.target_weights.append(tf.placeholder(dtype, shape=[None],
                                                  name="weight{0}".format(i)))

    # Our targets are decoder inputs shifted by one.
    targets = [self.decoder_inputs[i + 1]
               for i in xrange(len(self.decoder_inputs) - 1)]

    # Training outputs and losses.
    if forward_only:
        self.outputs, self.losses = tf.contrib.legacy_seq2seq.model_with_buckets(
            self.encoder_inputs, self.decoder_inputs, targets,
            self.target_weights, buckets, lambda x, y: seq2seq_f(x, y, True),
            softmax_loss_function=softmax_loss_function)
        # If we use output projection, we need to project outputs for decoding.
        if output_projection is not None:
            for b in xrange(len(buckets)):
                self.outputs[b] = [
                    tf.matmul(output, output_projection[0]) + output_projection[1]
                    for output in self.outputs[b]
                ]
    else:
        self.outputs, self.losses = tf.contrib.legacy_seq2seq.model_with_buckets(
            self.encoder_inputs, self.decoder_inputs, targets,
            self.target_weights, buckets,
            lambda x, y: seq2seq_f(x, y, False),
            softmax_loss_function=softmax_loss_function) # this is where the error occurrs

      

        
        
        
      

    

What do I need to change to get this to work? Using tensorflow version 1.2 function

UPDATE: This has been tested using both tensorflow built from source and built from Pip package on Mac OSX Sierra and this same issue occurs