tensorflow/models · error · ValueError

TransformerLayer expects a three-dimensional input of shape

Error message

TransformerLayer expects a three-dimensional input of shape [batch, sequence, width].

What it means

Error "TransformerLayer expects a three-dimensional input of shape [batch, sequence, width]." thrown in tensorflow/models.

Source

Thrown at official/nlp/modeling/layers/transformer_xl.py:128

    self._hidden_size = hidden_size
    self._inner_size = inner_size
    self._dropout_rate = dropout_rate
    self._attention_dropout_rate = attention_dropout_rate
    self._inner_activation = inner_activation
    self._norm_epsilon = norm_epsilon
    self._kernel_initializer = kernel_initializer
    self._inner_dropout = inner_dropout
    self._two_stream = two_stream
    if two_stream:
      self._attention_layer_type = relative_attention.TwoStreamRelativeAttention
    else:
      self._attention_layer_type = relative_attention.MultiHeadRelativeAttention

  def build(self, input_shape):
    input_tensor = input_shape[0] if len(input_shape) == 2 else input_shape
    input_tensor_shape = tf.TensorShape(input_tensor)
    if len(input_tensor_shape.as_list()) != 3:
      raise ValueError("TransformerLayer expects a three-dimensional input of "
                       "shape [batch, sequence, width].")
    batch_size, sequence_length, hidden_size = input_tensor_shape

    if len(input_shape) == 2:
      mask_tensor_shape = tf.TensorShape(input_shape[1])
      expected_mask_tensor_shape = tf.TensorShape(
          [batch_size, sequence_length, sequence_length])
      if not expected_mask_tensor_shape.is_compatible_with(mask_tensor_shape):
        raise ValueError("When passing a mask tensor to TransformerXLBlock, "
                         "the mask tensor must be of shape [batch, "
                         "sequence_length, sequence_length] (here %s). Got a "
                         "mask tensor of shape %s." %
                         (expected_mask_tensor_shape, mask_tensor_shape))
    if hidden_size % self._num_heads != 0:
      raise ValueError(
          "The input size (%d) is not a multiple of the number of attention "
          "heads (%d)" % (hidden_size, self._num_heads))
    self._attention_layer = self._attention_layer_type(

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/nlp/modeling/layers/transformer_xl.py:128 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of tensorflow/models@e006f5f0d5 (2026-08-24). Data as JSON: /api/errors/97fa1517becfce33. Report an issue: GitHub.