tensorflow/models · error · ValueError

`sequence_output` must be in decoder output.

Error message

`sequence_output` must be in decoder output.

What it means

Error "`sequence_output` must be in decoder output." thrown in tensorflow/models.

Source

Thrown at official/projects/perceiver/modeling/models/pretrainer.py:109

        'name': name,
    }

    self._decoder = decoder
    self.encoder = encoder
    encoder_inputs = self.encoder.inputs

    # Makes sure the weights are built.
    encoder_outputs = self.encoder(encoder_inputs)

    if 'sequence_output' not in encoder_outputs:
      if 'latent_output' in encoder_outputs and self._decoder is not None:
        decoder_inputs = {
            'latent_output': encoder_outputs['latent_output'],
            'input_mask': encoder_inputs['input_mask'],
        }
        decoder_outputs = self._decoder(decoder_inputs)
        if 'sequence_output' not in decoder_outputs:
          raise ValueError('`sequence_output` must be in decoder output.')
      else:
        raise ValueError('if `sequence_output` is not in encoder output, '
                         '`latent_output` must be in encoder output and'
                         'decoder must exist.')

    encoder_inputs = copy.copy(self.encoder.inputs)
    inputs = dict(encoder_inputs)

    if self._decoder is not None:
      inputs.update(copy.copy(self._decoder.inputs))

    self.masked_lm = customized_masked_lm or layers.MaskedLM(
        embedding_table=self.encoder.get_embedding_table(),
        activation=mlm_activation,
        initializer=mlm_initializer,
        name='cls/predictions')
    masked_lm_positions = tf_keras.layers.Input(
        shape=(None,), name='masked_lm_positions', dtype=tf.int32)

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/perceiver/modeling/models/pretrainer.py:109 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/01d2dcef6ac17391. Report an issue: GitHub.