tensorflow/models · error · ValueError

Unsupported activation `{}`.

Error message

Unsupported activation `{}`.

What it means

Error "Unsupported activation `{}`." thrown in tensorflow/models.

Source

Thrown at official/legacy/detection/modeling/architecture/nn_ops.py:75

      gamma_initializer = tf_keras.initializers.Zeros()
    else:
      gamma_initializer = tf_keras.initializers.Ones()
    self._normalization_op = tf_keras.layers.BatchNormalization(
        momentum=momentum,
        epsilon=epsilon,
        center=True,
        scale=True,
        trainable=trainable,
        fused=fused,
        gamma_initializer=gamma_initializer,
        name=name)
    self._use_activation = use_activation
    if activation == 'relu':
      self._activation_op = tf.nn.relu
    elif activation == 'swish':
      self._activation_op = tf.nn.swish
    else:
      raise ValueError('Unsupported activation `{}`.'.format(activation))

  def __call__(self, inputs, is_training=None):
    """Builds the normalization layer followed by an optional activation layer.

    Args:
      inputs: `Tensor` of shape `[batch, channels, ...]`.
      is_training: `boolean`, if True if model is in training mode.

    Returns:
      A normalized `Tensor` with the same `data_format`.
    """
    # We will need to keep training=None by default, so that it can be inherit
    # from keras.Model.training
    if is_training and self.trainable:
      is_training = True
    inputs = self._normalization_op(inputs, training=is_training)

    if self._use_activation:

View on GitHub (pinned to e006f5f0d5)

When it happens

Trigger: Thrown at official/legacy/detection/modeling/architecture/nn_ops.py:75 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/bba682b8cce693f9. Report an issue: GitHub.