tensorflow/models · error · ValueError

GroupConv2D expects input to be in channels_last format.

Error message

GroupConv2D expects input to be in channels_last format.

What it means

Error "GroupConv2D expects input to be in channels_last format." thrown in tensorflow/models.

Source

Thrown at official/projects/edgetpu/vision/modeling/custom_layers.py:113

        and `cols` values might have changed due to padding.

    Returns:
      A tensor of rank 4 representing
      `activation(GroupConv2D(inputs, kernel) + bias)`.

    Raises:
      ValueError: if groups < 1 or groups > filters
      ValueError: if data_format is not "channels_last".
      ValueError: if `padding` is not `same` or `valid`.
      ValueError: if `batch_norm_layer` is not a callable when provided.
      ValueError: when both `strides` > 1 and `dilation_rate` > 1.
    """
    if groups <= 1 or groups > filters:
      raise ValueError(f'Number of groups {groups} should be greater than 1 and'
                       f' less or equal than the output filters {filters}.')
    self._groups = groups
    if data_format != 'channels_last':
      raise ValueError(
          'GroupConv2D expects input to be in channels_last format.')

    if padding.lower() not in ('same', 'valid'):
      raise ValueError('Valid padding options are : same, or valid.')

    self.use_batch_norm = False
    if batch_norm_layer is not None:
      if not inspect.isclass(batch_norm_layer):
        raise ValueError('batch_norm_layer is not a class.')
      self.use_batch_norm = True
    self.bn_epsilon = bn_epsilon
    self.bn_momentum = bn_momentum
    self.batch_norm_layer = []
    if self.use_batch_norm:
      self.batch_norm_layer = [
          batch_norm_layer(  # pyrefly: ignore[not-callable]
              axis=-1, momentum=self.bn_momentum, epsilon=self.bn_epsilon)
          for i in range(self._groups)

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/edgetpu/vision/modeling/custom_layers.py:113 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/dca9c54354cfbb3a. Report an issue: GitHub.