tensorflow/models · error

Not a valid assemblenet_depth:

Error message

Not a valid assemblenet_depth:

What it means

Error "Not a valid assemblenet_depth:" thrown in tensorflow/models.

Source

Thrown at official/projects/assemblenet/modeling/assemblenet_plus.py:657

def assemblenet_plus(assemblenet_depth: int,
                     num_classes: int,
                     num_frames: int,
                     model_structure: List[Any],
                     input_specs: layers.InputSpec = layers.InputSpec(
                         shape=[None, None, None, None, 3]),
                     model_edge_weights: Optional[List[Any]] = None,
                     use_object_input: bool = False,
                     attention_mode: Optional[str] = None,
                     max_pool_predictions: bool = False,
                     **kwargs):
  """Returns the AssembleNet++ model for a given size and number of output classes."""

  data_format = tf_keras.backend.image_data_format()
  assert data_format == 'channels_last'

  if assemblenet_depth not in asn.ASSEMBLENET_SPECS:
    raise ValueError('Not a valid assemblenet_depth:', assemblenet_depth)

  if use_object_input:
    # assuming input_specs = [vide, obj] when use_object_input = True
    input_specs_dict = {'image': input_specs[0], 'object': input_specs[1]}
  else:
    input_specs_dict = {'image': input_specs}

  params = asn.ASSEMBLENET_SPECS[assemblenet_depth]
  backbone = AssembleNetPlus(
      block_fn=params['block'],
      num_blocks=params['num_blocks'],
      num_frames=num_frames,
      model_structure=model_structure,
      input_specs=input_specs,
      model_edge_weights=model_edge_weights,
      use_object_input=use_object_input,
      attention_mode=attention_mode,  # pyrefly: ignore[bad-argument-type]
      **kwargs)

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/assemblenet/modeling/assemblenet_plus.py:657 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/062103006f68eb3b. Report an issue: GitHub.