tensorflow/models · error · ValueError

Unknown Squeeze Excitation type {}

Error message

Unknown Squeeze Excitation type {}

What it means

Error "Unknown Squeeze Excitation type {}" thrown in tensorflow/models.

Source

Thrown at official/projects/movinet/modeling/movinet_layers.py:828

    """
    states = dict(states) if states is not None else {}

    if self._se_type == '3d':
      x, states = self._spatiotemporal_pool(
          inputs, states=states, output_states=True)
    elif self._se_type == '2d':
      x = self._spatial_pool(inputs)
    elif self._se_type == '2plus3d':
      x_space = self._spatial_pool(inputs)
      x, states = self._spatiotemporal_pool(
          x_space, states=states, output_states=True)

      if not self._causal:
        x = tf.tile(x, [1, tf.shape(inputs)[1], 1, 1, 1])

      x = tf.concat([x, x_space], axis=-1)
    else:
      raise ValueError('Unknown Squeeze Excitation type {}'.format(
          self._se_type))

    if self._pos_encoding is not None:
      x, states = self._pos_encoding(x, states=states)

    x = self._se_reduce(x)
    x = self._se_expand(x)

    return x * inputs, states


@tf_keras.utils.register_keras_serializable(package='Vision')
class MobileBottleneck(tf_keras.layers.Layer):
  """A depthwise inverted bottleneck block.

  Uses dependency injection to allow flexible definition of different layers
  within this block.
  """

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/movinet/modeling/movinet_layers.py:828 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/b518620fbbe84ce0. Report an issue: GitHub.