tensorflow/models · error · ValueError

multigrid has to match number of block_repeats

Error message

multigrid has to match number of block_repeats

What it means

Error "multigrid has to match number of block_repeats" thrown in tensorflow/models.

Source

Thrown at official/vision/modeling/backbones/resnet_deeplab.py:323

      inputs: A `tf.Tensor` of size `[batch, channels, height, width]`.
      filters: An `int` off number of filters for the first convolution of the
        layer.
      strides: An `int` of stride to use for the first convolution of the layer.
        If greater than 1, this layer will downsample the input.
      dilation_rate: An `int` of diluted convolution rates.
      block_fn: Either `nn_blocks.ResidualBlock` or `nn_blocks.BottleneckBlock`.
      block_repeats: An `int` of number of blocks contained in the layer.
      stochastic_depth_drop_rate: A `float` of drop rate of the current block
        group.
      multigrid: A list of `int` or None. If specified, dilation rates for each
        block is scaled up by its corresponding factor in the multigrid.
      name: A `str` name for the block.

    Returns:
      The output `tf.Tensor` of the block layer.
    """
    if multigrid is not None and len(multigrid) != block_repeats:
      raise ValueError('multigrid has to match number of block_repeats')

    if multigrid is None:
      multigrid = [1] * block_repeats

    # TODO(arashwan): move striding at the of the block.
    x = block_fn(
        filters=filters,
        strides=strides,
        dilation_rate=dilation_rate * multigrid[0],
        use_projection=True,
        stochastic_depth_drop_rate=stochastic_depth_drop_rate,
        se_ratio=self._se_ratio,
        resnetd_shortcut=self._resnetd_shortcut,
        kernel_initializer=self._kernel_initializer,
        kernel_regularizer=self._kernel_regularizer,
        bias_regularizer=self._bias_regularizer,
        activation=self._activation,
        use_sync_bn=self._use_sync_bn,

View on GitHub (pinned to e006f5f0d5)

Solutions

  1. Set multigrid to a list with one dilation value per block repeat (length must equal block_repeats).
  2. Set multigrid to None to disable multi-grid dilation.

When it happens

Trigger: Thrown at official/vision/modeling/backbones/resnet_deeplab.py:323 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/539a25aa425d0003. Report an issue: GitHub.