tensorflow/models · error · ValueError

Unsupported norm_type {norm_type}.

Error message

Unsupported norm_type {norm_type}.

What it means

Error "Unsupported norm_type {norm_type}." thrown in tensorflow/models.

Source

Thrown at official/projects/maxvit/modeling/layers.py:652

  if norm_type == 'layer_norm':
    return functools.partial(
        tf_keras.layers.LayerNormalization, epsilon=ln_epsilon
    )
  elif norm_type == 'batch_norm':
    return functools.partial(
        tf_keras.layers.BatchNormalization,
        momentum=bn_momentum,
        epsilon=bn_epsilon,
    )
  elif norm_type == 'sync_batch_norm':
    return functools.partial(
        tf_keras.layers.BatchNormalization,
        momentum=bn_momentum,
        epsilon=bn_epsilon,
        synchronized=True,
    )
  else:
    raise ValueError(f'Unsupported norm_type {norm_type}.')


def _build_downsample_layer(
    pool_type: str, pool_stride: int, data_format: str = 'channels_last'
) -> tf_keras.layers.Layer:
  """Builds a downsample layer for MbConv based on pool type."""
  if pool_type == 'max':
    return tf_keras.layers.MaxPooling2D(
        pool_size=(pool_stride, pool_stride),
        strides=(pool_stride, pool_stride),
        padding='same',
        data_format=data_format,
    )
  elif pool_type == 'avg':
    return tf_keras.layers.AveragePooling2D(
        pool_size=(pool_stride, pool_stride),
        strides=(pool_stride, pool_stride),
        padding='same',

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/maxvit/modeling/layers.py:652 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/f4e7faf8d50e59d7. Report an issue: GitHub.