tensorflow/models · error · NotImplementedError

Unsupported IBN type {block_op_type.type}.

Error message

Unsupported IBN type {block_op_type.type}.

What it means

Error "Unsupported IBN type {block_op_type.type}." thrown in tensorflow/models.

Source

Thrown at official/projects/edgetpu/vision/modeling/mobilenet_edgetpu_v2_model_blocks.py:98

      raise ValueError('Received skip type within block creation.')
    elif block_op_type.type == BlockType.ibn_dw:
      fused_expand = False
      fused_project = False
      conv_type = 'depthwise'
    elif block_op_type.type == BlockType.ibn_fused:
      fused_expand = True
      fused_project = False
      conv_type = 'full'
    elif block_op_type.type == BlockType.ibn_fused_grouped:
      fused_expand = True
      fused_project = False
      conv_type = 'group'
    elif block_op_type.type == BlockType.ibn_grouped:
      fused_expand = False
      fused_project = False
      conv_type = 'group'
    else:
      raise NotImplementedError(f'Unsupported IBN type {block_op_type.type}.')

    return cls.from_args(
        input_filters=input_filters,
        output_filters=output_filters,
        kernel_size=block_search_config.kernel_size,
        num_repeat=num_repeat,
        expand_ratio=block_search_config.expand_ratio,
        strides=(block_search_config.stride, block_search_config.stride),
        se_ratio=se_ratio,
        id_skip=id_skip,
        fused_expand=fused_expand,
        fused_project=fused_project,
        conv_type=conv_type,
        group_size=block_search_config.group_size)


@dataclasses.dataclass
class BlockGroupConfig(base_config.Config):

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/edgetpu/vision/modeling/mobilenet_edgetpu_v2_model_blocks.py:98 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/db3173f6807e2161. Report an issue: GitHub.