tensorflow/models · error · ValueError

Block func {} not supported.

Error message

Block func {} not supported.

What it means

Error "Block func {} not supported." thrown in tensorflow/models.

Source

Thrown at official/vision/modeling/backbones/efficientnet.py:238

  def _block_group(self,
                   inputs: tf.Tensor,
                   specs: BlockSpec,
                   name: str = 'block_group'):
    """Creates one group of blocks for the EfficientNet model.

    Args:
      inputs: A `tf.Tensor` of size `[batch, channels, height, width]`.
      specs: The specifications for one inverted bottleneck block group.
      name: A `str` name for the block.

    Returns:
      The output `tf.Tensor` of the block layer.
    """
    if specs.block_fn == 'mbconv':
      block_fn = nn_blocks.InvertedBottleneckBlock
    else:
      raise ValueError('Block func {} not supported.'.format(specs.block_fn))

    x = block_fn(
        in_filters=specs.in_filters,
        out_filters=specs.out_filters,
        expand_ratio=specs.expand_ratio,
        strides=specs.strides,
        kernel_size=specs.kernel_size,
        se_ratio=self._se_ratio,
        stochastic_depth_drop_rate=self._stochastic_depth_drop_rate,
        kernel_initializer=self._kernel_initializer,
        kernel_regularizer=self._kernel_regularizer,
        bias_regularizer=self._bias_regularizer,
        activation=self._activation,
        se_inner_activation=self._se_inner_activation,
        use_sync_bn=self._use_sync_bn,
        norm_momentum=self._norm_momentum,
        norm_epsilon=self._norm_epsilon)(
            inputs)

View on GitHub (pinned to e006f5f0d5)

Solutions

1. Use a supported block_fn for EfficientNet: 'mbconv' or 'fused_mbconv'.
2. Check the model config's block_fn value for typos.

When it happens

Trigger: Thrown at official/vision/modeling/backbones/efficientnet.py:238 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/e82cb2c72287d648. Report an issue: GitHub.