filter size and residual block repetition lists must have th

Error message

filter size and residual block repetition lists must have the same length

What it means

Error "filter size and residual block repetition lists must have the same length" thrown in tensorflow/models.

Source

Thrown at official/projects/centernet/modeling/layers/cn_nn_blocks.py:170

      blocks_per_stage: List[int], list of residual block repetitions per
        down/upsample. `blocks_per_stage[0]` defines the number of blocks at the
        current stage and `blocks_per_stage[1:]` is used at further stages.
        For example, [2, 2, 2, 2, 2, 4].
      strides: `int`, stride parameter to the Residual block.
      use_sync_bn: A `bool`, if True, use synchronized batch normalization.
      norm_momentum: `float`, momentum for the batch normalization layers.
      norm_epsilon: `float`, epsilon for the batch normalization layers.
      kernel_initializer: A `str` for kernel initializer of conv layers.
      kernel_regularizer: A `tf_keras.regularizers.Regularizer` object for
        Conv2D. Default to None.
      bias_regularizer: A `tf_keras.regularizers.Regularizer` object for Conv2D.
        Default to None.
      **kwargs: Additional keyword arguments to be passed.
    """
    super(HourglassBlock, self).__init__(**kwargs)

    if len(channel_dims_per_stage) != len(blocks_per_stage):
      raise ValueError('filter size and residual block repetition '
                       'lists must have the same length')

    self._num_stages = len(channel_dims_per_stage) - 1
    self._channel_dims_per_stage = channel_dims_per_stage
    self._blocks_per_stage = blocks_per_stage
    self._strides = strides
    self._use_sync_bn = use_sync_bn
    self._norm_momentum = norm_momentum
    self._norm_epsilon = norm_epsilon
    self._kernel_initializer = kernel_initializer
    self._kernel_regularizer = kernel_regularizer
    self._bias_regularizer = bias_regularizer

    self._filters = channel_dims_per_stage[0]
    if self._num_stages > 0:
      self._filters_downsampled = channel_dims_per_stage[1]

    self._reps = blocks_per_stage[0]

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/centernet/modeling/layers/cn_nn_blocks.py:170 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/6460304f7e4b371c. Report an issue: GitHub.