tensorflow/models · error · ValueError

Unsupported act_fn {}

Error message

Unsupported act_fn {}

What it means

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

Source

Thrown at official/projects/maxvit/modeling/common_ops.py:58

  elif act_fn == 'leaky_relu':
    return tf.nn.leaky_relu(features)
  elif act_fn == 'selu':
    return tf.nn.selu(features)
  elif act_fn == 'mish':
    return features * tf.math.tanh(tf.math.softplus(features))
  elif act_fn == 'gelu':
    return (
        0.5
        * features
        * (
            1
            + tf.tanh(
                np.sqrt(2 / np.pi) * (features + 0.044715 * tf.pow(features, 3))
            )
        )
    )
  else:
    raise ValueError('Unsupported act_fn {}'.format(act_fn))


def get_act_fn(act_fn):
  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

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/projects/maxvit/modeling/common_ops.py:58 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/1d8a723aff309246. Report an issue: GitHub.