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.py:375

      stochastic_depth_drop_rate: the base rate for stochastic depth.
      use_external_states: if True, expects states to be passed as additional
        input.
      output_states: if True, output intermediate states that can be used to run
          the model in streaming mode. Inputting the output states of the
          previous input clip with the current input clip will utilize a stream
          buffer for streaming video.
      average_pooling_type: The average pooling type. Currently supporting
        ['3d', '2d', 'none'].
      **kwargs: keyword arguments to be passed.
    """
    block_specs = BLOCK_SPECS[model_id]
    if input_specs is None:
      input_specs = tf_keras.layers.InputSpec(shape=[None, None, None, None, 3])

    if conv_type not in ('3d', '2plus1d', '3d_2plus1d'):
      raise ValueError('Unknown conv type: {}'.format(conv_type))
    if se_type not in ('3d', '2d', '2plus3d', 'none'):
      raise ValueError('Unknown squeeze excitation type: {}'.format(se_type))

    self._model_id = model_id
    self._block_specs = block_specs
    self._causal = causal
    self._use_positional_encoding = use_positional_encoding
    self._conv_type = conv_type
    self._se_type = se_type
    self._input_specs = input_specs
    self._use_sync_bn = use_sync_bn
    self._activation = activation
    self._gating_activation = gating_activation
    self._norm_momentum = norm_momentum
    self._norm_epsilon = norm_epsilon
    self._norm = tf_keras.layers.BatchNormalization
    self._kernel_initializer = kernel_initializer
    self._kernel_regularizer = kernel_regularizer
    self._bias_regularizer = bias_regularizer
    self._stochastic_depth_drop_rate = stochastic_depth_drop_rate

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/movinet/modeling/movinet.py:375 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/f7301022c8804f76. Report an issue: GitHub.