tensorflow/models · error · ValueError

Unexpected inputs type to %s.

Error message

Unexpected inputs type to %s.

What it means

Error "Unexpected inputs type to %s." thrown in tensorflow/models.

Source

Thrown at official/projects/perceiver/modeling/networks/sequence_encoder.py:141

    """Get embedding table."""
    return self._embedding_layer.embeddings

  def call(self,
           inputs: Dict[str, tf.Tensor],
           training: Optional[bool] = None) -> Dict[str, tf.Tensor]:
    """Return encoded and processed latent output of inputs.

    Args:
      inputs:
        Expect inputs to be a dictionary of `input_word_ids` and `input_mask`.
      training:
        Flag to indicate training status.

    Returns:
      `Dict[str, tf.Tensor]` decoded output of latent vector via the query.
    """
    if not isinstance(inputs, dict):
      raise ValueError('Unexpected inputs type to %s.' % self.__class__)
    word_ids = inputs['input_word_ids']
    input_mask = inputs.get('input_mask')

    word_embeddings = self._embedding_layer(word_ids)
    pos_encodings = self._input_pos_encoding(word_embeddings)
    embeddings = word_embeddings + pos_encodings

    tensor_for_shape = tf.ones(
        [tf.shape(embeddings)[0], self._z_index_dim, self._d_latents],
        dtype=embeddings.dtype)
    encoder_query = self._z_pos_enc(tensor_for_shape)

    z = self._encoder(
        [embeddings, encoder_query], input_mask=input_mask, training=training)
    return dict(latent_output=z)

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/perceiver/modeling/networks/sequence_encoder.py:141 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/2f7643895d1bbefe. Report an issue: GitHub.