tensorflow/models · error · ValueError

The number of input channels must be divisible by the number

Error message

The number of input channels must be divisible by the number of groups for evenly group split.

What it means

Error "The number of input channels must be divisible by the number of groups for evenly group split." thrown in tensorflow/models.

Source

Thrown at official/projects/mosaic/modeling/mosaic_blocks.py:108

    # helps quantization where conv+bn+activation are fused into a single op.
    self._activation_fn = tf_utils.get_activation(activation)
    if self._use_sync_bn:
      self._bn_op = tf_keras.layers.experimental.SyncBatchNormalization
    else:
      self._bn_op = tf_keras.layers.BatchNormalization

    if tf_keras.backend.image_data_format() == 'channels_last':
      self._bn_axis = -1
      self._group_split_axis = -1
    else:
      self._bn_axis = 1
      self._group_split_axis = 1

  def build(self, input_shape: tf.TensorShape) -> None:
    """Builds the block with the given input shape."""
    input_channels = input_shape[self._group_split_axis]
    if input_channels % self._num_groups != 0:
      raise ValueError('The number of input channels must be divisible by '
                       'the number of groups for evenly group split.')
    self._conv_branches = []
    if self._use_depthwise_convolution:
      for i, conv_kernel_size in enumerate(self._kernel_sizes):
        depthwise_conv = tf_keras.layers.DepthwiseConv2D(
            kernel_size=(conv_kernel_size, conv_kernel_size),
            depth_multiplier=1,
            padding='same',
            depthwise_regularizer=self._kernel_regularizer,
            depthwise_initializer=self._kernel_initializer,
            use_bias=False)
        # Add BN->RELU after depthwise convolution.
        batchnorm_op_depthwise = self._bn_op(
            axis=self._bn_axis,
            momentum=self._batchnorm_momentum,
            epsilon=self._batchnorm_epsilon)
        activation_depthwise = self._activation_fn
        feature_conv = tf_keras.layers.Conv2D(

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/mosaic/modeling/mosaic_blocks.py:108 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/5df26be1d5623d87. Report an issue: GitHub.