tensorflow/models · error · ValueError

Unsurpported pool_type %s

Error message

Unsurpported pool_type %s

What it means

Error "Unsurpported pool_type %s" thrown in tensorflow/models.

Source

Thrown at official/projects/maxvit/modeling/common_ops.py:80

  if act_fn is None:
    act_fn = 'gelu'
  if isinstance(act_fn, str):
    return functools.partial(activation_fn, act_fn=act_fn)
  elif callable(act_fn):
    return act_fn
  else:
    raise ValueError('Unsupported act_fn %s.' % act_fn)


def pooling_2d(inputs, pool_type, stride, **kwargs):
  """Perform 2D pooling."""
  if stride > 1:
    if pool_type == 'max':
      pool_op = tf_keras.layers.MaxPool2D
    elif pool_type == 'avg':
      pool_op = tf_keras.layers.AveragePooling2D
    else:
      raise ValueError('Unsurpported pool_type %s' % pool_type)
    output = pool_op(
        pool_size=(stride, stride), strides=(stride, stride), **kwargs
    )(inputs)
  else:
    output = inputs
  return output


def drop_connect(inputs, training, survival_prob):
  """Drop the entire conv with given survival probability."""
  # "Deep Networks with Stochastic Depth", https://arxiv.org/pdf/1603.09382.pdf
  if not training:
    return inputs

  # Compute tensor.
  batch_size = tf.shape(inputs)[0]
  random_tensor = survival_prob
  random_tensor += tf.random.uniform([batch_size], dtype=inputs.dtype)

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/maxvit/modeling/common_ops.py:80 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/e759e4c4ebc0bcef. Report an issue: GitHub.