tensorflow/models · error · ValueError

Number of input channels: {input_channel} are not divisible

Error message

Number of input channels: {input_channel} are not divisible by number of groups: {self._groups}.

What it means

Error "Number of input channels: {input_channel} are not divisible by number of groups: {self._groups}." thrown in tensorflow/models.

Source

Thrown at official/projects/edgetpu/vision/modeling/custom_layers.py:158

        dilation_rate=dilation_rate,
        activation=activation,
        use_bias=use_bias,
        kernel_initializer=kernel_initializer,
        bias_initializer=bias_initializer,
        kernel_regularizer=kernel_regularizer,
        bias_regularizer=bias_regularizer,
        activity_regularizer=activity_regularizer,
        kernel_constraint=kernel_constraint,
        bias_constraint=bias_constraint,
        groups=1,
        **kwargs)  # pytype: disable=bad-return-type  # typed-keras

  def build(self, input_shape: tuple[int, ...]) -> None:
    """Builds GroupConv2D layer as a collection of smaller Conv2D layers."""
    input_shape = tf.TensorShape(input_shape)
    input_channel = self._get_input_channel(input_shape)
    if input_channel % self._groups != 0:
      raise ValueError(
          f'Number of input channels: {input_channel} are not divisible '
          f'by number of groups: {self._groups}.')

    self.group_input_channel = int(input_channel / self._groups)
    self.group_output_channel = int(self.filters / self._groups)  # pyrefly: ignore[unsupported-operation]
    self.group_kernel_shape = self.kernel_size + (self.group_input_channel,
                                                  self.group_output_channel)

    self.kernel = []
    self.bias = []
    for g in range(self._groups):
      self.kernel.append(
          self.add_weight(
              name='kernel_{}'.format(g),
              shape=self.group_kernel_shape,
              initializer=tf_utils.clone_initializer(self.kernel_initializer),
              regularizer=self.kernel_regularizer,
              constraint=self.kernel_constraint,

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/edgetpu/vision/modeling/custom_layers.py:158 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/3c78fff938d757a0. Report an issue: GitHub.