tensorflow/models · error · ValueError

Number of groups should be greater than 1 and less than the

Error message

Number of groups should be greater than 1 and less than the output filters.

What it means

Error "Number of groups should be greater than 1 and less than the output filters." thrown in tensorflow/models.

Source

Thrown at official/projects/edgetpu/vision/modeling/custom_layers.py:314

      data_format: The ordering of the dimensions in the inputs. `channels_last`
        corresponds to inputs with shape `(batch_size, height, width, channels)`
      padding: one of `"valid"` or `"same"` (case-insensitive).
      **kwargs: Additional keyword arguments passed to the underlying conv
        layers.

    Raises:
      ValueError: if groups < 1 or groups > filters
      ValueError: if `batch_norm_layer` is not a callable when provided.
      ValueError: if `data_format` is not channels_last
      ValueError: if `padding` is not `same` or `valid`.
    """
    super().__init__()
    self.conv_layers = []
    self.bn_layers = []
    per_conv_filter_size = filters / groups

    if groups <= 1 or groups >= filters:
      raise ValueError('Number of groups should be greater than 1 and less '
                       'than the output filters.')

    self.batch_norm_layer = batch_norm_layer
    self.use_batch_norm = False
    if self.batch_norm_layer is not None:
      if not inspect.isclass(self.batch_norm_layer):  # pytype: disable=not-supported-yet
        raise ValueError('batch_norm_layer is not a class.')
      self.use_batch_norm = True

    if 'activation' in kwargs.keys():
      self.activation = tf_keras.activations.get(kwargs['activation'])
      kwargs.pop('activation')
    else:
      self.activation = None

    if data_format != 'channels_last':
      raise ValueError(
          'GroupConv2D expects input to be in channels_last format.')

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/edgetpu/vision/modeling/custom_layers.py:314 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/c480359083e3623d. Report an issue: GitHub.